analiza aiqbench
This research addresses a critical misattribution flaw in 3D intrinsic decomposition by introducing Proximity Attention Point Rendering (PAPR) for direct per-point supervision. By replacing volume rendering with ray-surface intersection predictions, the method achieves superior albedo estimation and novel view synthesis compared to NeRF-based and diffusion approaches. The work represents a significant advancement in inverse rendering architectures and machine learning applications for 3D scene understanding.
Intrinsic PAPR: Tackling Misattribution in 3D Intrinsic Decomposition via Proximity Attention Point Rendering
arXiv:2407.00500v2 Announce Type: replace-cross Abstract: Recent point-based intrinsic decomposition and inverse rendering methods have advanced the modelling of the shading and albedo of 3D scenes. However, we identify a fundamental limitation: these methods suffer from a misattribution issue, where individual primitives learn incorrect appearance features despite producing correct aggregated renderings. We show that the root cause lies in volume rendering, which aggregates translucent primitives along each ray and only supervises the final colour, preventing direct supervision of individual primitive features. To address this, we propose Intrinsic PAPR, a robust intrinsic decomposition framework which leverages Proximity Attention Point Rendering (PAPR) to enable direct per-point supervision. Unlike volume rendering approaches, PAPR eliminates translucent primitives and directly predicts appearance at ray-surface intersections, enabling accurate supervision to the feature of each individual point. Our method incorporates a 2D albedo prior adapted with conditional Implicit Maximum Likelihood Estimation (cIMLE) to handle monocular ambiguities, and employs a space carving loss to ensure multi-view consistency. Extensive evaluations on synthetic and real-world datasets demonstrate that Intrinsic PAPR outperforms point-based inverse rendering, NeRF-based intrinsic decomposition, and diffusion-based PBR methods in novel view synthesis and albedo estimation while resolving the misattribution issue.
Abstract:Recent point-based intrinsic decomposition and inverse rendering methods have advanced the modelling of the shading and albedo of 3D scenes. However, we identify a fundamental limitation: these methods suffer from a misattribution issue, where individual primitives learn incorrect appearance features despite producing correct aggregated renderings. We show that the root cause lies in volume rendering, which aggregates translucent primitives along each ray and only supervises the final colour, preventing direct supervision of individual primitive features. To address this, we propose Intrinsic PAPR, a robust intrinsic decomposition framework which leverages Proximity Attention Point Rendering (PAPR) to enable direct per-point supervision. Unlike volume rendering approaches, PAPR eliminates translucent primitives and directly predicts appearance at ray-surface intersections, enabling accurate supervision to the feature of each individual point. Our method incorporates a 2D albedo prior adapted with conditional Implicit Maximum Likelihood Estimation (cIMLE) to handle monocular ambiguities, and employs a space carving loss to ensure multi-view consistency. Extensive evaluations on synthetic and real-world datasets demonstrate that Intrinsic PAPR outperforms point-based inverse rendering, NeRF-based intrinsic decomposition, and diffusion-based PBR methods in novel view synthesis and albedo estimation while resolving the misattribution issue.
Accepted to ECCV 2026. 21 pages + 34-page supplementary material
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Graphics (cs.GR); Machine Learning (cs.LG)
arXiv:2407.00500 [cs.CV]
(or arXiv:2407.00500v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2407.00500 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 300 cuvinte
Subiecte conexe
From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data
arXiv · 12 iun. 2026
AWS Deepens Strategic Collaboration with QuEra to Bring Fault-Tolerant Quantum Computing to Amazon Braket
AWS · 15 iun. 2026
The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologically Regularized Side-Path
arXiv · 24 iul. 2026
IMFACT: Counterfactual Explanations for Time Series via Intrinsic Mode Function Substitution
arXiv · 6 aug. 2026