Pith. sign in

REVIEW 6 cited by

Differentiable Rendering: A Survey

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2006.12057 v2 pith:GBPSVX2X submitted 2020-06-22 cs.CV cs.GR

Hiroharu Kato , Deniz Beker , Mihai Morariu , Takahiro Ando , Toru Matsuoka , Wadim Kehl , Adrien Gaidon This is my paper
classification cs.CVcs.GR
keywords differentiablerenderingapplicationsimageobjectssuccessallowsalways
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep neural networks (DNNs) have shown remarkable performance improvements on vision-related tasks such as object detection or image segmentation. Despite their success, they generally lack the understanding of 3D objects which form the image, as it is not always possible to collect 3D information about the scene or to easily annotate it. Differentiable rendering is a novel field which allows the gradients of 3D objects to be calculated and propagated through images. It also reduces the requirement of 3D data collection and annotation, while enabling higher success rate in various applications. This paper reviews existing literature and discusses the current state of differentiable rendering, its applications and open research problems.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Physically-Based Inverse Rendering Framework for PET Image Reconstruction

    physics.med-ph 2025-08 conditional novelty 6.0 of 10

    A differentiable rendering framework performs PET reconstruction as gradient-based optimization, matching MLEM while enabling physics-based forward modeling.

  2. InverTwin: Solving Inverse Problems via Differentiable Radio Frequency Digital Twin

    eess.SP 2025-08 reject novelty 6.0 of 10

    A differentiable RF digital twin framework that inverts radar observations into scene parameters using path-space differentiation and a smooth radar surrogate model.

  3. GaussianGAN: Real-Time Photorealistic controllable Human Avatars

    cs.CV 2025-09 conditional novelty 5.0 of 10

    GaussianGAN generates photorealistic human avatars in real time by densifying Gaussian points around skeleton limbs and refining rendered features with a UNet.

  4. Disentangled Geometry and Appearance for Efficient Multi-View Surface Reconstruction and Rendering

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    A disentangled geometry-and-appearance model over explicit meshes with differentiable rasterization achieves fast training and rendering for multi-view reconstruction.

  5. Multi-View Face and Gesture Animation with Dynamic Gaussians

    cs.CV 2026-08 conditional novelty 4.0 of 10

    Combining separate face and hand models with a parametric body and Gaussian splatting enables multi-view-consistent upper-body avatars that can be re-animated with new expressions and gestures.

  6. Reconstructing 4D Spatial Intelligence: A Survey

    cs.CV 2025-07 accept novelty 4.0 of 10

    A review that classifies 4D scene reconstruction methods into five progressive levels: low-level cues, scene components, dynamic scenes, interactions, and physics.

Pith tools