Pith. sign in

REVIEW 24 cited by

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

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 2003.08934 v2 pith:46U44JHP submitted 2020-03-19 cs.CV cs.GR

classification cs.CVcs.GR
keywords viewviewsinputneuralradiancerenderingresultsscenes
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene using a fully-connected (non-convolutional) deep network, whose input is a single continuous 5D coordinate (spatial location $(x,y,z)$ and viewing direction $(\theta, \phi)$) and whose output is the volume density and view-dependent emitted radiance at that spatial location. We synthesize views by querying 5D coordinates along camera rays and use classic volume rendering techniques to project the output colors and densities into an image. Because volume rendering is naturally differentiable, the only input required to optimize our representation is a set of images with known camera poses. We describe how to effectively optimize neural radiance fields to render photorealistic novel views of scenes with complicated geometry and appearance, and demonstrate results that outperform prior work on neural rendering and view synthesis. View synthesis results are best viewed as videos, so we urge readers to view our supplementary video for convincing comparisons.

Discussion (0). Sign in to comment.

Forward citations

Cited by 24 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 527 citations worldwide. 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. PRISM3D: Probabilistic Refinement and Robust Initialization for Physically Consistent Scene Modeling under Extreme Motion Blur

    cs.CV 2026-07 conditional novelty 6.5 of 10

    PRISM3D bootstraps 3D Gaussian Splatting from extreme motion blur via VGGSfM initialization, MCMC densification, and Bézier trajectories, with an event-assisted extension that sets new SOTA.

  3. SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    SubdivAR reformulates neural mesh subdivision as autoregressive next-scale vertex-offset prediction, reporting 18.8% lower Hausdorff and 14.2% lower Chamfer distance than NMR on closed meshes.

  4. You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    YOGO reformulates stochastic 3D Gaussian Splatting into a deterministic budget-aware system and supplies an ultra-dense dataset to enforce physical fidelity over viewpoint interpolation.

  5. GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation

    cs.CV 2026-03 conditional novelty 6.0 of 10

    A causal transformer with 3D RoPE generates vector-quantized 3D Gaussian latent grids autoregressively, enabling unconditional synthesis, completion, and open-ended outpainting of indoor scenes.

  6. PokeNet: Learning Kinematic Models of Articulated Objects from Human Observations

    cs.RO 2026-02 conditional novelty 6.0 of 10

    PokeNet estimates joint types, axes, ranges, and operation order of articulated objects directly from a single-view point cloud video of a human demonstration.

  7. Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments

    cs.LG 2026-01 conditional novelty 6.0 of 10

    Flow equivariant world models use a latent memory that shifts with the agent and with inferred object motion, giving stable long-horizon prediction under partial observability.

  8. MRD: Using Physically Based Differentiable Rendering to Probe Vision Models for 3D Scene Understanding

    cs.CV 2025-12 conditional novelty 6.0 of 10

    MRD finds physically different 3D scenes that reproduce a target model activation, revealing which shape and material properties vision models are sensitive to.

  9. Deformable Medical Image Registration with KAN-based Implicit Neural Representations

    cs.CV 2025-09 conditional novelty 6.0 of 10

    KAN-based implicit neural networks with randomized basis sampling outperform existing INR registration methods on three medical imaging datasets at lower computational cost.

  10. LuxDiT: Lighting Estimation with Video Diffusion Transformer

    cs.GR 2025-09 conditional novelty 6.0 of 10

    A video diffusion transformer fine-tuned on synthetic and real data predicts HDR environment maps from images/videos, cutting peak light-direction error by roughly 45% on sunny outdoor scenes versus DiffusionLight.

  11. SLRTP2025 Sign Language Production Challenge: Methodology, Results, and Future Work

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    A first competitive benchmark for sign language production, with a hidden test set, retrieval-based winning systems, and a released evaluation network.

  12. Variational volume reconstruction with the Deep Ritz Method

    eess.IV 2025-08 unverdicted novelty 6.0 of 10

    A Deep Ritz variational method with a modified Cahn-Hilliard regularizer reconstructs volumes from sparse noisy slices without segmentation.

  13. GraphBrep: Learning B-Rep in Graph Structure for Efficient CAD Generation

    cs.CV 2025-07 conditional novelty 6.0 of 10

    GraphBrep replaces the redundant tree-based topology of prior B-Rep generators with an explicit graph adjacency representation, cutting training and inference cost while preserving generation quality.

  14. RoadVGGT: Road-Structure-Aware Feed-Forward Road Surface Reconstruction

    cs.CV 2026-07 conditional novelty 5.5 of 10

    A feed-forward Gaussian head on OmniVGGT plus road-plane grid fusion and structure-aware grouping reconstructs compact road surfaces that beat RoGS and AnySplat on Waymo and zero-shot nuScenes.

  15. Quo Vadis, World Modeling?

    cs.CV 2026-08 conditional novelty 5.0 of 10

    An agent-centric reframing of world modeling, replacing physical state prediction with 'information transitions' organized into six proxy functions and three empowerment levels.

  16. Towards optimal photometric calibration of digital astronomical plates with deep learning

    astro-ph.IM 2026-08 conditional novelty 5.0 of 10

    A deep network that jointly models magnitude, color, and position dependence improves photometric calibration of digitized photographic plates, roughly halving bright-star errors versus the separable MYX25 method.

  17. Quantifying and Attributing Power Flexibility from GPU-Heavy Data Centers

    eess.SY 2026-03 unverdicted novelty 5.0 of 10

    Energy-aware scheduling yields latent GPU-data-center power flexibility via cooling shifts (~$30/MWh) and job movement/reordering ($30–$3000+/MWh), larger with perfect queue foresight.

  18. DiskChunGS: Large-Scale 3D Gaussian SLAM Through Chunk-Based Memory Management

    cs.RO 2025-11 conditional novelty 5.0 of 10

    Storing inactive spatial chunks of a 3D Gaussian map on disk and loading only camera-visible chunks into GPU memory lets DiskChunGS map all 11 KITTI sequences on a 24 GB GPU without memory failures.

  19. DIPOLE: Fusing Vision and Geometry for Robust Visuomotor Generalization

    cs.RO 2025-11 conditional novelty 5.0 of 10

    Fusing RGB and point-cloud inputs with training-time modality dropout plus cross-attention makes a diffusion visuomotor policy markedly more robust to visual and spatial shifts than unimodal or naively fused baselines.

  20. HairGS: Hair Strand Reconstruction based on 3D Gaussian Splatting

    cs.CV 2025-09 conditional novelty 5.0 of 10

    HairGS reconstructs 3D hair strands from multi-view images in about one hour by fitting 3D Gaussians, merging them into strands with distance and direction rules, and refining them against the photos.

  21. Construction of Digital Terrain Maps from Multi-view Satellite Imagery using Neural Volume Rendering

    cs.CV 2025-08 unverdicted novelty 5.0 of 10

    Neural terrain maps reconstruct digital elevation models from multi-view satellite imagery alone, reaching near image-resolution accuracy.

  22. Sequential Neural Operator Transformer for High-Fidelity Surrogates of Time-Dependent Non-linear Partial Differential Equations

    physics.comp-ph 2025-07 conditional novelty 5.0 of 10

    S-NOT, a GRU-transformer hybrid, predicts full-field solutions of time-dependent nonlinear PDEs with lower error than Sequential DeepONet on steel solidification, 3D lug, and dogbone benchmarks.

  23. Real-Time Scene Reconstruction using Light Field Probes

    cs.GR 2025-07 conditional novelty 4.0 of 10

    A probe-based renderer built from laser point clouds reconstructs a room-scale scene in real time with constant per-frame cost.

  24. From images to properties: a NeRF-driven framework for granular material parameter inversion

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A pipeline combining NeRF 3D reconstruction, MPM simulation, and Bayesian optimization recovers sand friction angle from rendered images with mean absolute errors between 0.64 and 1.38 degrees in synthetic tests.

Pith tools