Pith. sign in

REVIEW 12 cited by

RAFT: Recurrent All-Pairs Field Transforms for Optical Flow

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 2003.12039 v3 pith:LDXO7ENT submitted 2020-03-26 cs.CV

Zachary Teed , Jia Deng This is my paper · ORCID
classification cs.CV
keywords rafterrorfieldflowpixelsrecurrentachievesall-pairs
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D correlation volumes for all pairs of pixels, and iteratively updates a flow field through a recurrent unit that performs lookups on the correlation volumes. RAFT achieves state-of-the-art performance. On KITTI, RAFT achieves an F1-all error of 5.10%, a 16% error reduction from the best published result (6.10%). On Sintel (final pass), RAFT obtains an end-point-error of 2.855 pixels, a 30% error reduction from the best published result (4.098 pixels). In addition, RAFT has strong cross-dataset generalization as well as high efficiency in inference time, training speed, and parameter count. Code is available at https://github.com/princeton-vl/RAFT.

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. WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    WorldRoamBench is a new benchmark for interactive world models that evaluates four stability dimensions with custom metrics and finds no tested model performs reliably across all.

  2. FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds

    cs.AI 2026-08 conditional novelty 6.0 of 10

    FactorJEPA splits a video prediction model into layout, agent, and interaction channels with a visibility gate, and a new DENSEWORLD dataset tests it on crowded Indian city scenes.

  3. Vision-Language-Motion Maps: An Open-Vocabulary, Uncertainty-Aware, Queryable Motion Attribute for 3D Scene Maps

    cs.RO 2026-07 conditional novelty 6.0 of 10

    VLMM is a 3D map representation where each object carries a fused, uncertainty-aware motion attribute (language-based movability prior + observed geometric motion) that makes motion queries such as 'what is moving' an...

  4. Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders

    cs.CV 2026-04 conditional novelty 6.0 of 10

    Spatio-temporal contrastive SAEs recover temporal coherence lost by hard TopK, improve action probes by +3.9% and retrieval by up to 2.8× R@1, and expose a monosemanticity metric artifact.

  5. Scaling Up Audio-Synchronized Visual Animation: An Efficient Training Paradigm

    cs.CV 2025-08 conditional novelty 6.0 of 10

    An audio-conditioned video animation model is pretrained on noisy auto-curated videos and fine-tuned on a few clean examples, achieving top synchronization scores on a new 48-class benchmark with only 1.9% additional ...

  6. Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Motion-X++ provides 19.5M 3D whole-body pose annotations across 120.5K sequences with text, audio, video, and motion modalities.

  7. GeoRoute: Geometry-Aware Hybrid Inference for Traffic Future-Frame Prediction

    cs.CV 2026-08 conditional novelty 5.0 of 10

    A geometry-aware, training-free inference framework that refines pretrained video diffusion predictions with projected static history content and view-conditioned routing achieves fifth place on AI City Challenge Track 5.

  8. A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data

    cs.AI 2026-01 conditional novelty 5.0 of 10

    A metric-oriented survey that classifies intrinsic quality and trustworthiness metrics for LLM-generated data across six modalities and documents systematic evaluation gaps in the current literature.

  9. Adam SLAM - the last mile of camera calibration with 3DGS

    cs.CV 2025-08 conditional novelty 5.0 of 10

    Backpropagating the 3D Gaussian Splatting color loss into camera parameters, with an L2 loss, focal-length training, and a Hessian-based reparameterization, raises average PSNR by 0.4 dB over COLMAP calibration on ref...

  10. HKT: A Biologically Inspired Framework for Modular Hereditary Knowledge Transfer in Neural Networks

    cs.LG 2025-08 conditional novelty 5.0 of 10

    HKT is a modular feature-level distillation method whose genetic attention residual improves compact vision models on optical flow, classification, and segmentation benchmarks.

  11. CosmosAlign: Adapting a World Foundation Model for Generative Traffic Video Forecasting

    cs.CV 2026-08 conditional novelty 4.0 of 10

    CosmosAlign adapts Cosmos3-Nano with two-stage LoRA, medoid sample selection, and motion-adaptive blending, achieving first place (76.49) on the AI City Challenge 2026 Track 5 traffic video forecasting benchmark.

  12. Uncertainty Aware Mapping for Vision-Based Underwater Robots

    cs.RO 2025-07 conditional novelty 4.0 of 10

    A vision-based underwater mapping pipeline that colors Voxblox TSDF maps with RAFT-Stereo depth confidence and replaces weight accumulation with a running average.

Pith tools