Pith. sign in

REVIEW 12 cited by

Instant Neural Graphics Primitives with a Multiresolution Hash Encoding

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 2201.05989 v2 pith:5ZW7XOXU submitted 2022-01-16 cs.CV cs.GRcs.LG

Thomas Müller , Alex Evans , Christoph Schied , Alexander Keller This is my paper · ORCID
classification cs.CVcs.GRcs.LG
keywords neuralgraphicshashmultiresolutionnetworkprimitivesencodingoperations
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that permits the use of a smaller network without sacrificing quality, thus significantly reducing the number of floating point and memory access operations: a small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through stochastic gradient descent. The multiresolution structure allows the network to disambiguate hash collisions, making for a simple architecture that is trivial to parallelize on modern GPUs. We leverage this parallelism by implementing the whole system using fully-fused CUDA kernels with a focus on minimizing wasted bandwidth and compute operations. We achieve a combined speedup of several orders of magnitude, enabling training of high-quality neural graphics primitives in a matter of seconds, and rendering in tens of milliseconds at a resolution of ${1920\!\times\!1080}$.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

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

  1. StreamME: Simplify 3D Gaussian Avatar within Live Stream

    cs.GR 2025-07 conditional novelty 7.0 of 10

    StreamME reconstructs an animatable head avatar from a live monocular video in about five minutes by attaching 3D Gaussian points to a tracked face mesh and pruning unimportant points during training.

  2. NeRF-based CBCT Reconstruction needs Normalization and Initialization

    eess.IV 2025-06 conditional novelty 6.0 of 10

    Adding layer normalization between the hash encoder and the MLP, plus initializing the network from a dense-volume pretrained model, improves NeRF-based CBCT reconstruction speed and quality.

  3. VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A new RGBD SLAM representation ties Gaussian positions to depth pixels, leaving only color, radius, and opacity learnable, enabling local-only optimization and higher rendering quality on several benchmarks.

  4. Query Quantized Neural SLAM

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Quantizing neural SLAM queries into discrete codes speeds up per-frame overfitting and improves reconstruction completion and tracking accuracy on RGB-D benchmarks.

  5. Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functions

    cs.CV 2024-12 conditional novelty 6.0 of 10

    The paper builds small surface patches in the neural SDF field during volume rendering and imposes depth, normal, and photo-consistency losses on them, reporting improved indoor reconstruction.

  6. 4DPV: 4D Pet from Videos by Coarse-to-Fine Non-Rigid Radiance Fields

    cs.CV 2024-11 conditional novelty 6.0 of 10

    A coarse-to-fine neural network learns camera pose and 4D shape of deforming objects from multiple RGB videos, adding a local quadratic deformation model to a BANMo-style neural radiance field.

  7. 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.

  8. 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.

  9. UAV4D: Dynamic Neural Rendering of Human-Centric UAV Imagery using Gaussian Splatting

    cs.CV 2025-06 conditional novelty 5.0 of 10

    UAV4D reconstructs 4D scenes from monocular drone video by fitting a single global scale to align human meshes with the background mesh, then renders with separate Gaussian splats.

  10. Puzzle Similarity: A Perceptually-guided Cross-Reference Metric for Artifact Detection in 3D Scene Reconstructions

    cs.CV 2024-11 conditional novelty 5.0 of 10

    Puzzle Similarity detects artifacts in novel views of 3D scenes by max-pooling feature similarity against training views, and it outperforms prior quality metrics in correlating with human artifact segmentations.

  11. BayesSDF: Surface-Based Laplacian Uncertainty Estimation for 3D Geometry with Neural Signed Distance Fields

    cs.CV 2025-07 reject novelty 4.0 of 10

    BayesSDF estimates surface uncertainty as aggregated squared color gradients with respect to a hash-encoded deformation field, and reports correlation with depth error on four benchmark scenes.

  12. NeurNCD: Novel Class Discovery via Implicit Neural Representation

    cs.LG 2025-06 reject novelty 4.0 of 10

    NeurNCD proposes a NeRF-based framework for novel class discovery in RGB-D scenes, claiming superior mIoU on NYUv2 and Replica, though the presented implementation is internally inconsistent.

Pith tools