arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2606.18486cs.GRcs.ITmath.IT
收藏

渲染分离信息:凸分离场景的率失真重建

Rendering Separoid Information: Rate-Distortion Reconstruction of Convex Apartness Scenes

Bahçeşehir University(巴切谢希尔大学)

Faruk Alpay, Baris Basaran

AI总结:

将凸体的分离结构视为源信号,提出一种率失真框架,通过可微支撑函数实现软分离表示,并推导分离互信息的变分下界,实验表明从分离表可高精度恢复场景。

摘要:

一个凸场景传达的不仅仅是形状:哪些物体组相互分离、哪些交叉的模式是一种离散的关系负载。我们将有限族凸体的分离表(一个分离体)视为源信号;可渲染的凸场景作为其编码器;渲染图像作为有噪视觉通道,从中解码分离结构。对于不相交的索引集$A,B$,源比特记录$\operatorname{conv}(\bigcup_{a\in A} C_a)$和$\operatorname{conv}(\bigcup_{b\in B} C_b)$是否不相交。在此视角下,保持分离的渲染成为一个率失真问题:率是载体场景的可微几何编码长度,而失真是闭包感知的,并通过它们控制的结果数量对最大分离和最小Radon划分进行加权。可微支撑函数实现将可分离性转化为软方向间隔,并将每个分离表示为见证方向上的分布,从而得到分离互信息$I(\Sigma;Y)$的变分下界以及视图选择的信息论解释。在平面凸场景上的实验表明,仅从分离表即可恢复场景,比特准确率达99.9%,证书骨架已确定完整表格;坐标量化给出了清晰的操作率失真边界,其中证书失真比汉明误差更严格;渲染的$48\times48$图像在轻微噪声下传输约0.72的分离图熵。增加视角鲁棒性项会加宽分离锥,仅带来适度的几何率代价。结果是一个证书感知的渲染目标,适用于其目的是使关系凸结构可恢复而非仅仅像素保真的场景。

英文摘要:

A convex scene communicates more than shape: the pattern of which groups of objects are mutually apart and which cross is a discrete relational payload. We treat the apartness table of a finite family of convex bodies, a separoid, as a source signal; a renderable convex scene as its encoder; and the rendered image as a noisy visual channel from which the apartness structure is decoded. For disjoint index sets $A,B$, the source bit records whether $\operatorname{conv}(\bigcup_{a\in A} C_a)$ and $\operatorname{conv}(\bigcup_{b\in B} C_b)$ are disjoint. Within this view, apartness-preserving rendering becomes a rate--distortion problem: the rate is a differentiable geometric code length for the carrier scene, while the distortion is closure-aware and weights maximal separations and minimal Radon partitions by the number of consequences they control. A differentiable support-function realization turns separability into a soft directional margin and represents each separation by a distribution over witnessing directions, yielding a variational lower bound on apartness mutual information $I(Σ;Y)$ and an information-theoretic account of view selection. Experiments on planar convex scenes show that scenes are recovered from the apartness table alone at 99.9% bit accuracy, with the certificate skeleton already determining the full table; coordinate quantization gives a clean operational rate--distortion frontier where certificate distortion is more stringent than Hamming error; and rendered $48\times48$ images transmit about 0.72 of the apartness-graph entropy under mild noise. Increasing the viewpoint-robustness term widens separating cones with only a modest geometry-rate surcharge. The result is a certificate-aware rendering objective for scenes whose purpose is to make relational convex structure recoverable rather than merely pixel-faithful.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑