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
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.
Forward citations
Cited by 22 Pith papers
-
Detangled: A Framework for Creating, Editing, and Inferencing Feature Rich Hair Strands
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.
-
Instant Expressive Gaussian Head Avatars at Over 100 FPS
A single-photo avatar encoder with per-Gaussian feature-space deformation animates faces at 107 FPS with expression quality competitive with diffusion models.
-
DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos
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.
-
Style4D-Bench: A Benchmark Suite for 4D Stylization
Style4D-Bench introduces a 12-metric evaluation protocol and a 4DGS-based baseline, Style4D, claimed to achieve state-of-the-art 4D stylization.
-
E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras
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.
-
Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video
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.
-
Laplacian Analysis Meets Dynamics Modelling: Gaussian Splatting for 4D Reconstruction
A Laplacian-enhanced hybrid encoding method for 4D Gaussian Splatting that claims better reconstruction fidelity for dynamic scenes.
-
Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis
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.
-
STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene
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.
-
Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry
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.
-
Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation
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.
-
FreeTimeGS: Free Gaussian Primitives at Anytime and Anywhere for Dynamic Scene Reconstruction
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.
-
Low-Rank Head Avatar Personalization with Registers
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.
-
TOM-GS: Editable Video Representation via Temporal Opacity Modulation of Static 3D Gaussians
A video can be modeled by static 3D Gaussians with a learnable per-Gaussian temporal opacity window, yielding an editable 3D asset.
-
Interaction-Aware 4D Gaussian Splatting for Dynamic Hand-Object Interaction Reconstruction
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.
-
Leveraging 2D Priors and SDF Guidance for Dynamic Urban Scene Rendering
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.
-
Enhanced Velocity Field Modeling for Gaussian Video Reconstruction
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.
-
SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction
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.
-
LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling
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...
-
SkinningGS: Editable Dynamic Human Scene Reconstruction Using Gaussian Splatting Based on a Skinning Model
A UV-texture-driven Gaussian splatting avatar method claims faster, leaner, and better human-scene reconstruction than HUGS, but its tables contain internal inconsistencies.
-
Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction
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...
-
Reconstructing 4D Spatial Intelligence: A Survey
A review that classifies 4D scene reconstruction methods into five progressive levels: low-level cues, scene components, dynamic scenes, interactions, and physics.
Discussion (0). Continue with ORCID to comment.