NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models
Comments CVPR 2023
期刊&会议
CVPR
Conference on Computer Vision and Pattern Recognition · 会议 · Computer Vision
K-means Clustering Based Feature Consistency Alignment for Label-free Model Evaluation
Comments Accepted by CVPR 2023 workshop
Sampling is Matter: Point-guided 3D Human Mesh Reconstruction
Comments Accepted by CVPR 2023
Investigating the Nature of 3D Generalization in Deep Neural Networks
Comments 15 pages, 15 figures, CVPR format
MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors
Comments Accepted by CVPR 2023
Look ATME: The Discriminator Mean Entropy Needs Attention
Comments Accepted for the CVPR 2023 Workshop on Generative Models for Computer Vision, https://generative-vision.github.io/workshop-CVPR-23/
Parcel3D: Shape Reconstruction from Single RGB Images for Applications in Transportation Logistics
Comments Accepted at CVPR workshop on Vision-based InduStrial InspectiON (VISION) 2023, see https://vision-based-industrial-inspection.github.io/cvpr-2023/
Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes
Comments Accepted by CVPR 2023. Code and models are available at: https://github.com/ruili3/dynamic-multiframe-depth
SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenes
Comments To appear in CVPR 2023
Quantum Annealing for Single Image Super-Resolution
Comments Accepted to IEEE/CVF CVPR 2023, NTIRE Challenge and Workshop. Draft info: 10 pages, 6 Figures, 2 Tables
Perceive, Excavate and Purify: A Novel Object Mining Framework for Instance Segmentation
Comments Accepted by CVPR Workshops 2023
Motion-state Alignment for Video Semantic Segmentation
Comments Accepted by CVPR Workshops 2023
SViTT: Temporal Learning of Sparse Video-Text Transformers
Comments CVPR 2023
AdaMTL: Adaptive Input-dependent Inference for Efficient Multi-Task Learning
Comments This paper will appear in the proceedings of CVPR 2023
U2RLE: Uncertainty-Guided 2-Stage Room Layout Estimation
Comments To be Appear on CVPR 2023
Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model
Comments CVPR 2023, project page: https://dulucas.github.io/agrol/
Single Image Depth Prediction Made Better: A Multivariate Gaussian Take
Comments Accepted to IEEE/CVF CVPR 2023. Draft info: 17 pages, 13 Figures, 9 Tables
VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
Comments CVPR 2023 camera-ready version
Benchmarking Self-Supervised Learning on Diverse Pathology Datasets
Comments Accepted to CVPR 2023
Prototypical Residual Networks for Anomaly Detection and Localization
Comments Accepted by CVPR 2023
Revisiting Rolling Shutter Bundle Adjustment: Toward Accurate and Fast Solution
Comments Accepted to CVPR 2023
Rebalancing Batch Normalization for Exemplar-based Class-Incremental Learning
Comments CVPR 2023 camera ready
Delving into Shape-aware Zero-shot Semantic Segmentation
Comments Accepted to CVPR 2023, code: https://github.com/Liuxinyv/SAZS
Conditional Generation of Audio from Video via Foley Analogies
Comments CVPR 2023
Affordances from Human Videos as a Versatile Representation for Robotics
Comments Accepted at CVPR 2023. Website at https://robo-affordances.github.io/
DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training
Comments To appear in CVPR 2023 as a highlight, our code will be public at https://github.com/IDEA-Research/DisCo-CLIP
Learning to Render Novel Views from Wide-Baseline Stereo Pairs
Comments CVPR 2023, Project Webpage: https://yilundu.github.io/wide_baseline/, Last Two Authors Equal Advising
SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing
Comments 10 pages, 7 figures, CVPR Workshop
OVTrack: Open-Vocabulary Multiple Object Tracking
Comments CVPR 2023
Learning Geometry-aware Representations by Sketching
Comments CVPR 2023
