Generating high-quality camera-controllable videos from monocular input is a challenging task, particularly under extreme viewpoint. Existing methods often struggle with geometric inconsistencies and occlusion artifacts in boundaries, leading to degraded visual quality. In this paper, we introduce EX-4D, a novel framework that addresses these challenges through a Depth Watertight Mesh representation. The representation serves as a robust geometric prior by explicitly modeling both visible and occluded regions, ensuring geometric consistency in extreme camera pose. To overcome the lack of paired multi-view datasets, we propose a simulated masking strategy that generates effective training data only from monocular videos. Additionally, a lightweight LoRA-based video diffusion adapter is employed to synthesize high-quality, physically consistent, and temporally coherent videos. Extensive experiments demonstrate that EX-4D outperforms state-of-the-art methods in terms of physical consistency and extreme-view quality, enabling practical 4D video generation.
Ghost on the Shell: An Expressive Representation of General 3D Shapes
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；ETH Zürich（苏黎世联邦理工学院）；University of Cambridge（剑桥大学）
Reconstructing 3D non-watertight mesh from an unoriented point cloud is an unexplored area in computer vision and computer graphics. In this project, we tried to tackle this problem by extending the learning-based watertight mesh reconstruction pipeline presented in the paper 'Shape as Points'. The core of our approach is to cast the problem as a semantic segmentation problem that identifies the region in the 3D volume where the mesh surface lies and extracts the surfaces from the detected regions. Our approach achieves compelling results compared to the baseline techniques.
Given an "in-the-wild" video of a person, we reconstruct an animatable model of the person in the video. The output model can be rendered in any body pose to any camera view, via the learned controls, without explicit 3D mesh reconstruction. At the core of our method is a volumetric 3D human representation reconstructed with a deep network trained on input video, enabling novel pose/view synthesis. Our method is an advance over GAN-based image-to-image translation since it allows image synthesis for any pose and camera via the internal 3D representation, while at the same time it does not requ…
While NeRF-based 3D-aware image generation methods enable viewpoint control, limitations still remain to be adopted to various 3D applications. Due to their view-dependent and light-entangled volume representation, the 3D geometry presents unrealistic quality and the color should be re-rendered for every desired viewpoint. To broaden the 3D applicability from 3D-aware image generation to 3D-controllable object generation, we propose the factorized representations which are view-independent and light-disentangled, and training schemes with randomly sampled light conditions. We demonstrate the s…
In this paper, we report on a parallel freeviewpoint video synthesis algorithm that can efficiently reconstruct a high-quality 3D scene representation of sports scenes. The proposed method focuses on a scene that is captured by multiple synchronized cameras featuring wide-baselines. The following strategies are introduced to accelerate the production of a free-viewpoint video taking the improvement of visual quality into account: (1) a sparse point cloud is reconstructed using a volumetric visual hull approach, and an exact 3D ROI is found for each object using an efficient connected component…
In this paper we present, to the best of our knowledge, the first method to learn a generative model of 3D shapes from natural images in a fully unsupervised way. For example, we do not use any ground truth 3D or 2D annotations, stereo video, and ego-motion during the training. Our approach follows the general strategy of Generative Adversarial Networks, where an image generator network learns to create image samples that are realistic enough to fool a discriminator network into believing that they are natural images. In contrast, in our approach the image generation is split into 2 stages. In…
DreamMesh: Jointly Manipulating and Texturing Triangle Meshes for Text-to-3D Generation
School of Computer Science, Fudan University（复旦大学计算机科学学院）；HiDream.ai Inc.（HiDream.ai公司）；Shanghai Collaborative Innovation Center of Intelligent Visual Computing（上海智能视觉计算协同创新中心）
High fidelity representation of shapes with arbitrary topology is an important problem for a variety of vision and graphics applications. Owing to their limited resolution, classical discrete shape representations using point clouds, voxels and meshes produce low quality results when used in these applications. Several implicit 3D shape representation approaches using deep neural networks have been proposed leading to significant improvements in both quality of representations as well as the impact on downstream applications. However, these methods can only be used to represent topologically c…
Geometric Deep Learning has recently made striking progress with the advent of continuous Deep Implicit Fields. They allow for detailed modeling of watertight surfaces of arbitrary topology while not relying on a 3D Euclidean grid, resulting in a learnable parameterization that is not limited in resolution. Unfortunately, these methods are often not suitable for applications that require an explicit mesh-based surface representation because converting an implicit field to such a representation relies on the Marching Cubes algorithm, which cannot be differentiated with respect to the underlying…
University of Bonn（波恩大学）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Although commercial and open-source software exist to reconstruct a static object from a sequence recorded with an RGB-D sensor, there is a lack of tools that build rigged models of articulated objects that deform realistically and can be used for tracking or animation. In this work, we fill this gap and propose a method that creates a fully rigged model of an articulated object from depth data of a single sensor. To this end, we combine deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow. The fully rigged model then consi…
One Video, One World: Turning Monocular Video into Physical 4D Scenes
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；SparcAI Inc（SparcAI公司）；University of Science and Technology of China（中国科学技术大学）；The Hong Kong Polytechnic University（香港理工大学）；University of Electronic Science and Technology of China（电子科技大学）；Nanyang Technological University（南洋理工大学）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）
Queen Mary University of London（伦敦玛丽女王大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
Novel-View Human Action Synthesis aims to synthesize the movement of a body from a virtual viewpoint, given a video from a real viewpoint. We present a novel 3D reasoning to synthesize the target viewpoint. We first estimate the 3D mesh of the target body and transfer the rough textures from the 2D images to the mesh. As this transfer may generate sparse textures on the mesh due to frame resolution or occlusions. We produce a semi-dense textured mesh by propagating the transferred textures both locally, within local geodesic neighborhoods, and globally, across symmetric semantic parts. Next, w…
Ulm University（乌尔姆大学）；Universitat Politècnica de Catalunya（加泰罗尼亚理工大学）
Optimal viewpoint prediction is an essential task in many computer graphics applications. Unfortunately, common viewpoint qualities suffer from two major drawbacks: dependency on clean surface meshes, which are not always available, and the lack of closed-form expressions, which requires a costly search involving rendering. To overcome these limitations we propose to separate viewpoint selection from rendering through an end-to-end learning approach, whereby we reduce the influence of the mesh quality by predicting viewpoints from unstructured point clouds instead of polygonal meshes. While th…
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；Neural Concept；Interl Labs（Interl实验室）；Meta Reality Labs（Meta现实实验室）
Geometric Deep Learning has recently made striking progress with the advent of continuous deep implicit fields. They allow for detailed modeling of watertight surfaces of arbitrary topology while not relying on a 3D Euclidean grid, resulting in a learnable parameterization that is unlimited in resolution. Unfortunately, these methods are often unsuitable for applications that require an explicit mesh-based surface representation because converting an implicit field to such a representation relies on the Marching Cubes algorithm, which cannot be differentiated with respect to the underlying imp…
The University of Hong Kong（香港大学）；University College London（伦敦大学学院）；Texas A&M University（德克萨斯A&M大学）
We introduce Point2Skeleton, an unsupervised method to learn skeletal representations from point clouds. Existing skeletonization methods are limited to tubular shapes and the stringent requirement of watertight input, while our method aims to produce more generalized skeletal representations for complex structures and handle point clouds. Our key idea is to use the insights of the medial axis transform (MAT) to capture the intrinsic geometric and topological natures of the original input points. We first predict a set of skeletal points by learning a geometric transformation, and then analyze…
Simon Fraser University（西蒙弗雷泽大学）；Google Brain（谷歌大脑）
Polygonal meshes are ubiquitous, but have only played a relatively minor role in the deep learning revolution. State-of-the-art neural generative models for 3D shapes learn implicit functions and generate meshes via expensive iso-surfacing. We overcome these challenges by employing a classical spatial data structure from computer graphics, Binary Space Partitioning (BSP), to facilitate 3D learning. The core operation of BSP involves recursive subdivision of 3D space to obtain convex sets. By exploiting this property, we devise BSP-Net, a network that learns to represent a 3D shape via convex d…
We study the problem of shape generation in 3D mesh representation from a few color images with known camera poses. While many previous works learn to hallucinate the shape directly from priors, we resort to further improving the shape quality by leveraging cross-view information with a graph convolutional network. Instead of building a direct mapping function from images to 3D shape, our model learns to predict series of deformations to improve a coarse shape iteratively. Inspired by traditional multiple view geometry methods, our network samples nearby area around the initial mesh's vertex l…
Neural Radiance Fields for Novel View Synthesis in Monocular Gastroscopy
Tokyo Institute of Technology（东京工业大学）；International University of Health and Welfare Ichikawa Hospital（国际医疗福祉大学市川医院）；Tsujinaka Hospital Kashiwanoha（辻仲医院柏之叶）
Oxford Robotics Institute, University of Oxford（牛津大学牛津机器人研究所）
Building good 3D maps is a challenging and expensive task, which requires high-quality sensors and careful, time-consuming scanning. We seek to reduce the cost of building good reconstructions by correcting views of existing low-quality ones in a post-hoc fashion using learnt priors over surfaces and appearance. We train a CNN model to predict the difference in inverse-depth from varying viewpoints of two meshes -- one of low quality that we wish to correct, and one of high-quality that we use as a reference. In contrast to previous work, we pay attention to the problem of excessive smoothing …
University of Pennsylvania（宾夕法尼亚大学）；Amazon.com, Inc（亚马逊公司）
Human reconstruction and synthesis from monocular RGB videos is a challenging problem due to clothing, occlusion, texture discontinuities and sharpness, and framespecific pose changes. Many methods employ deferred rendering, NeRFs and implicit methods to represent clothed humans, on the premise that mesh-based representations cannot capture complex clothing and textures from RGB, silhouettes, and keypoints alone. We provide a counter viewpoint to this fundamental premise by optimizing a SMPL+D mesh and an efficient, multi-resolution texture representation using only RGB images, binary silhouet…
We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses. While many previous works learn to hallucinate the shape directly from priors, we adopt to further improve the shape quality by leveraging cross-view information with a graph convolution network. Instead of building a direct mapping function from images to 3D shape, our model learns to predict series of deformations to improve a coarse shape iteratively. Inspired by traditional multiple view geometry methods, our network samples nearby area around the initial mes…
Interactive Rendering of Relightable and Animatable Gaussian Avatars
State Key Lab of CAD & CG, Zhejiang University（浙江大学计算机辅助设计与图形学国家重点实验室）；UCL Centre for Artificial Intelligence, Department of Computer Science, University College London（伦敦大学学院计算机科学系人工智能中心）；Kahlert School of Computing, University of Utah（犹他大学Kahlert计算学院）
The Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）；Adobe Research（Adobe研究）
In this paper, we address the problem of 3D object mesh reconstruction from RGB videos. Our approach combines the best of multi-view geometric and data-driven methods for 3D reconstruction by optimizing object meshes for multi-view photometric consistency while constraining mesh deformations with a shape prior. We pose this as a piecewise image alignment problem for each mesh face projection. Our approach allows us to update shape parameters from the photometric error without any depth or mask information. Moreover, we show how to avoid a degeneracy of zero photometric gradients via rasterizin…
There has been great progress in human 3D mesh recovery and great interest in learning about the world from consumer video data. Unfortunately current methods for 3D human mesh recovery work rather poorly on consumer video data, since on the Internet, unusual camera viewpoints and aggressive truncations are the norm rather than a rarity. We study this problem and make a number of contributions to address it: (i) we propose a simple but highly effective self-training framework that adapts human 3D mesh recovery systems to consumer videos and demonstrate its application to two recent systems; (i…
We present TexMesh, a novel approach to reconstruct detailed human meshes with high-resolution full-body texture from RGB-D video. TexMesh enables high quality free-viewpoint rendering of humans. Given the RGB frames, the captured environment map, and the coarse per-frame human mesh from RGB-D tracking, our method reconstructs spatiotemporally consistent and detailed per-frame meshes along with a high-resolution albedo texture. By using the incident illumination we are able to accurately estimate local surface geometry and albedo, which allows us to further use photometric constraints to adapt…
Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Saarland University（萨尔大学）；Saarbrücken Research Center for Visual Computing, Interaction and AI（萨尔布吕肯视觉计算、交互与人工智能研究中心）
Bharati Vidyapeeth’s College of Engineering（巴拉蒂维迪亚佩斯工程学院）
In this paper, we propose a novel pipeline for the 3D reconstruction of the full body from egocentric viewpoints. 3-D reconstruction of the human body from egocentric viewpoints is a challenging task as the view is skewed and the body parts farther from the cameras are occluded. One such example is the view from cameras installed below VR headsets. To achieve this task, we first make use of conditional GANs to translate the egocentric views to full body third-person views. This increases the comprehensibility of the image and caters to occlusions. The generated third-person view is further sen…
SuperCarver: Texture-Consistent 3D Geometry Super-Resolution for High-Fidelity Surface Detail Generation
Tencent Games, China（腾讯游戏，中国）；Department of Computer Science & Engineering, Texas A & M University（电子与计算机工程系，德克萨斯A&M大学）；Department of Computer Science, City University of Hong Kong（计算机科学系，香港城市大学）
We present a novel approach for tracking multiple people in video. Unlike past approaches which employ 2D representations, we focus on using 3D representations of people, located in three-dimensional space. To this end, we develop a method, Human Mesh and Appearance Recovery (HMAR) which in addition to extracting the 3D geometry of the person as a SMPL mesh, also extracts appearance as a texture map on the triangles of the mesh. This serves as a 3D representation for appearance that is robust to viewpoint and pose changes. Given a video clip, we first detect bounding boxes corresponding to peo…
We present a learning framework that learns to recover the 3D shape, pose and texture from a single image, trained on an image collection without any ground truth 3D shape, multi-view, camera viewpoints or keypoint supervision. We approach this highly under-constrained problem in a "analysis by synthesis" framework where the goal is to predict the likely shape, texture and camera viewpoint that could produce the image with various learned category-specific priors. Our particular contribution in this paper is a representation of the distribution over cameras, which we call "camera-multiplex". I…
To generalize to novel visual scenes with new viewpoints and new object poses, a visual system needs representations of the shapes of the parts of an object that are invariant to changes in viewpoint or pose. 3D graphics representations disentangle visual factors such as viewpoints and lighting from object structure in a natural way. It is possible to learn to invert the process that converts 3D graphics representations into 2D images, provided the 3D graphics representations are available as labels. When only the unlabeled images are available, however, learning to derender is much harder. We…
