Pith. sign in

REVIEW 7 cited by

Instant Neural Graphics Primitives with a Multiresolution Hash Encoding

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

classification cs.CVcs.GRcs.LG
keywords neuralgraphicshashmultiresolutionnetworkprimitivesencodingoperations
verification ladder T0 review T1 audit T2 compute T3 formal
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). Sign in to comment.

Forward citations

Cited by 7 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. 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.

  3. 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.

  4. 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.

  5. 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.

  6. 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.

  7. 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