Pith. sign in

REVIEW 22 cited by

HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields

Not yet reviewed by Pith; the record is open.

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 2106.13228 v2 pith:TU4JWH35 submitted 2021-06-24 cs.CV cs.GR

classification cs.CVcs.GR
keywords hypernerfdeformationfieldfieldsinputmethodradiancescenes
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Neural Radiance Fields (NeRF) are able to reconstruct scenes with unprecedented fidelity, and various recent works have extended NeRF to handle dynamic scenes. A common approach to reconstruct such non-rigid scenes is through the use of a learned deformation field mapping from coordinates in each input image into a canonical template coordinate space. However, these deformation-based approaches struggle to model changes in topology, as topological changes require a discontinuity in the deformation field, but these deformation fields are necessarily continuous. We address this limitation by lifting NeRFs into a higher dimensional space, and by representing the 5D radiance field corresponding to each individual input image as a slice through this "hyper-space". Our method is inspired by level set methods, which model the evolution of surfaces as slices through a higher dimensional surface. We evaluate our method on two tasks: (i) interpolating smoothly between "moments", i.e., configurations of the scene, seen in the input images while maintaining visual plausibility, and (ii) novel-view synthesis at fixed moments. We show that our method, which we dub HyperNeRF, outperforms existing methods on both tasks. Compared to Nerfies, HyperNeRF reduces average error rates by 4.1% for interpolation and 8.6% for novel-view synthesis, as measured by LPIPS. Additional videos, results, and visualizations are available at https://hypernerf.github.io.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 22 Pith papers

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

  1. Detangled: A Framework for Creating, Editing, and Inferencing Feature Rich Hair Strands

    cs.CV 2026-07 conditional novelty 7.0 of 10

    A 5D texture parameterization plus centerline-based canonical space and supervised diffusion enables generation and texture transfer of feature-rich hair strands independent of style.

  2. Instant Expressive Gaussian Head Avatars at Over 100 FPS

    cs.CV 2025-12 conditional novelty 7.0 of 10

    A single-photo avatar encoder with per-Gaussian feature-space deformation animates faces at 107 FPS with expression quality competitive with diffusion models.

  3. DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos

    cs.GR 2025-06 conditional novelty 7.0 of 10

    A single feed-forward transformer predicts per-pixel deformable 3D Gaussians with dense scene flow from a posed monocular video, enabling real-time dynamic view synthesis and 3D tracking.

  4. Style4D-Bench: A Benchmark Suite for 4D Stylization

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Style4D-Bench introduces a 12-metric evaluation protocol and a 4DGS-based baseline, Style4D, claimed to achieve state-of-the-art 4D stylization.

  5. E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras

    cs.CV 2025-08 conditional novelty 6.0 of 10

    E-4DGS is a deformable 3D Gaussian Splatting method that reconstructs dynamic scenes directly from multi-view event camera streams, outperforming event-to-image baseline approaches.

  6. Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Video-rewinding joint training preserves geometry while re-animating a single-video scene with novel motion from a text prompt and an image-to-video model.

  7. Laplacian Analysis Meets Dynamics Modelling: Gaussian Splatting for 4D Reconstruction

    cs.GR 2025-08 unverdicted novelty 6.0 of 10

    A Laplacian-enhanced hybrid encoding method for 4D Gaussian Splatting that claims better reconstruction fidelity for dynamic scenes.

  8. Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A video-to-4D model that encodes mesh animations into compact Gaussian variation latents and diffuses them conditioned on the video and a canonical Gaussian splat.

  9. STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene

    cs.CV 2025-06 conditional novelty 6.0 of 10

    STD-GS disentangles background and dynamic objects by clustering frame appearance and event motion features, and uses event brightness and flow to supervise Gaussian rendering, improving high-dynamic scene reconstruction.

  10. Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Vid-CamEdit re-synthesizes monocular videos along user-defined camera paths by conditioning a video diffusion model on 2D flows derived from estimated 3D geometry, without training on multi-view video data.

  11. Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation

    cs.GR 2025-06 conditional novelty 6.0 of 10

    Vid2Sim recovers 3D geometry, appearance, and elastic material parameters from multi-view videos using a feed-forward network plus a fast refinement, enabling mesh-free reduced-order simulation.

  12. FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A dynamic-scene representation where Gaussian primitives live freely in 4D space-time with linear motion and Gaussian time windows achieves state-of-the-art novel-view quality on complex-motion benchmarks.

  13. Low-Rank Head Avatar Personalization with Registers

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A Register Module, a learnable 3D feature space rigged to a 3DMM mesh, improves LoRA-based personalization of head avatars by teaching the model to focus on identity-specific DINOv2 features during adaptation.

  14. TOM-GS: Editable Video Representation via Temporal Opacity Modulation of Static 3D Gaussians

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A video can be modeled by static 3D Gaussians with a learnable per-Gaussian temporal opacity window, yielding an editable 3D asset.

  15. Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction

    cs.CV 2025-11 conditional novelty 5.0 of 10

    A 4D Gaussian-splatting method with separate hand/object/background fields, learned importance and radius parameters, and hand-conditioned object deformation improves dynamic hand-object reconstruction from egocentric video.

  16. Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Rendering

    cs.CV 2025-10 conditional novelty 5.0 of 10

    UGSDF achieves state-of-the-art novel-view rendering of dynamic urban objects without LiDAR or 3D motion annotations by jointly optimizing SDFs and 3D Gaussians under 2D depth and point-tracking priors.

  17. Enhanced Velocity Field Modeling for Gaussian Video Reconstruction

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Velocity field rendering with flow-based losses and flow-assisted densification lifts dynamic Gaussian novel-view PSNR by about 2.5 dB on Nvidia-long and Neu3D.

  18. SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction

    cs.GR 2025-07 conditional novelty 5.0 of 10

    SD-GS combines anchor-based 3D Gaussians with a deformation field and a deformation-aware densification strategy to reconstruct dynamic scenes more compactly and faster than prior 4D Gaussian methods.

  19. LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling

    cs.CV 2025-07 conditional novelty 5.0 of 10

    LocalDyGS reconstructs dynamic scenes by decomposing space into seed-based local regions and generating time-varying Temporal Gaussians, though its claim of being first for large-scale scenes omits the existing Swift4...

  20. SkinningGS: Editable Dynamic Human Scene Reconstruction Using Gaussian Splatting Based on a Skinning Model

    cs.GR 2025-06 conditional novelty 5.0 of 10

    A UV-texture-driven Gaussian splatting avatar method claims faster, leaner, and better human-scene reconstruction than HUGS, but its tables contain internal inconsistencies.

  21. Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A 3D Gaussian Splatting framework for urban scenes that combines visibility-based data partitioning, budgeted level-of-detail generation, and per-Gaussian appearance embeddings to enable efficient training and real-ti...

  22. 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