Intrinsicnerf: Learning intrinsic neural radiance fields for editable novel view synthesis

W Ye, S Chen, C Bao, H Bao… - Proceedings of the …, 2023 - openaccess.thecvf.com
Existing inverse rendering combined with neural rendering methods can only perform
editable novel view synthesis on object-specific scenes, while we present intrinsic neural …

Estimating reflectance layer from a single image: Integrating reflectance guidance and shadow/specular aware learning

Y Jin, R Li, W Yang, RT Tan - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Estimating the reflectance layer from a single image is a challenging task. It becomes more
challenging when the input image contains shadows or specular highlights, which often …

Intrinsic image decomposition via ordinal shading

C Careaga, Y Aksoy - ACM Transactions on Graphics, 2023 - dl.acm.org
Intrinsic decomposition is a fundamental mid-level vision problem that plays a crucial role in
various inverse rendering and computational photography pipelines. Generating highly …

Umat: Uncertainty-aware single image high resolution material capture

C Rodriguez-Pardo… - Proceedings of the …, 2023 - openaccess.thecvf.com
We propose a learning-based method to recover normals, specularity, and roughness from a
single diffuse image of a material, using microgeometry appearance as our primary cue …

RGB↔ X: Image decomposition and synthesis using material-and lighting-aware diffusion models

Z Zeng, V Deschaintre, I Georgiev… - ACM SIGGRAPH 2024 …, 2024 - dl.acm.org
The three areas of realistic forward rendering, per-pixel inverse rendering, and generative
image synthesis may seem like separate and unrelated sub-fields of graphics and vision …

[HTML][HTML] Materialistic: Selecting similar materials in images

P Sharma, J Philip, M Gharbi, B Freeman, F Durand… - 2023 - history.siggraph.org
Separating an image into meaningful underlying components is a crucial first step for both
editing and understanding images. We present a method capable of selecting the regions of …

Split: Single portrait lighting estimation via a tetrad of face intrinsics

F Fei, Y Cheng, Y Zhu, Q Zheng, S Li… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
This paper proposes a novel pipeline to estimate a non-parametric environment map with
high dynamic range from a single human face image. Lighting-independent and-dependent …

Concept distillation: leveraging human-centered explanations for model improvement

A Gupta, S Saini, PJ Narayanan - Advances in Neural …, 2024 - proceedings.neurips.cc
Humans use abstract concepts for understanding instead of hard features. Recent
interpretability research has focused on human-centered concept explanations of neural …

Measured albedo in the wild: Filling the gap in intrinsics evaluation

J Wu, S Chowdhury, H Shanmugaraja… - 2023 IEEE …, 2023 - ieeexplore.ieee.org
Intrinsic image decomposition and inverse rendering are long-standing problems in
computer vision. To evaluate albedo recovery, most algorithms report their quantitative …

Intrinsicdiffusion: Joint intrinsic layers from latent diffusion models

J Luo, D Ceylan, JS Yoon, N Zhao, J Philip… - ACM SIGGRAPH 2024 …, 2024 - dl.acm.org
Reasoning about the intrinsic properties of an image, such as albedo, illumination, and
surface geometry, is a long-standing problem with many applications in image editing and …