Pith. sign in

REVIEW 7 cited by

Bilateral Reference for High-Resolution Dichotomous Image Segmentation

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 2401.03407 v7 pith:D5REZQ3F submitted 2024-01-07 cs.CV

Peng Zheng , Dehong Gao , Deng-Ping Fan , Li Liu , Jorma Laaksonen , Wanli Ouyang , Nicu Sebe This is my paper
classification cs.CV
keywords referencebilateralbirefnetbirefcomponentsdichotomousgradienthigh-resolution
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce a novel bilateral reference framework (BiRefNet) for high-resolution dichotomous image segmentation (DIS). It comprises two essential components: the localization module (LM) and the reconstruction module (RM) with our proposed bilateral reference (BiRef). The LM aids in object localization using global semantic information. Within the RM, we utilize BiRef for the reconstruction process, where hierarchical patches of images provide the source reference and gradient maps serve as the target reference. These components collaborate to generate the final predicted maps. We also introduce auxiliary gradient supervision to enhance focus on regions with finer details. Furthermore, we outline practical training strategies tailored for DIS to improve map quality and training process. To validate the general applicability of our approach, we conduct extensive experiments on four tasks to evince that BiRefNet exhibits remarkable performance, outperforming task-specific cutting-edge methods across all benchmarks. Our codes are available at https://github.com/ZhengPeng7/BiRefNet.

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. S3OD: Towards Generalizable Salient Object Detection with Synthetic Data

    cs.CV 2025-10 conditional novelty 7.0 of 10

    A 139k-image synthetic dataset with diffusion- and DINO-derived masks, trained with a multi-mask decoder, improves cross-dataset salient-object detection and reaches state-of-the-art after fine-tuning.

  2. Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoning

    cs.CV 2025-12 conditional novelty 6.0 of 10

    A dual-module network with iterative light/geometry feedback detects cast and attached shadows separately and outperforms prior methods on a new 1,458-image benchmark.

  3. ANYPORTAL: Zero-Shot Consistent Video Background Replacement

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A training-free video background replacement pipeline that keeps the foreground pixel-consistent by projecting refined latents through a deterministic reparameterization.

  4. DreamDance: Animating Character Art via Inpainting Stable Gaussian Worlds

    cs.CV 2025-05 conditional novelty 6.0 of 10

    DreamDance animates a single character artwork by reconstructing its background as a 3D Gaussian scene and then inpainting the animated character into the rendered video.

  5. Boosting Monocular Metric Depth Estimation via Bokeh Rendering

    cs.CV 2025-12 reject novelty 5.0 of 10

    A two-stage method that synthesizes bokeh stacks from one image and uses them to boost the metric accuracy of monocular depth estimation.

  6. Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Reinforcement learning can teach an LMM to prompt SAM2 for segmentation, achieving competitive camouflaged and salient object detection and zero-shot referring segmentation.

  7. ToonOut: Fine-tuned Background-Removal for Anime Characters

    cs.CV 2025-09 conditional novelty 4.0 of 10

    Fine-tuning BiRefNet on a small synthetic anime dataset lifts their test-set pixel accuracy from 95.3% to 99.5%, but the test set is curated from the same distribution.

Pith tools