Bilateral Reference for High-Resolution Dichotomous Image Segmentation
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.
This paper has not been read by Pith yet.
Forward citations
Cited by 7 Pith papers
-
LiWi: Layering in the Wild
LiWi uses an agent-driven data synthesis pipeline to build the LiWi-100k dataset and a model with shadow-guided and degradation-restoration objectives that achieves SoTA performance on RGB L1 and Alpha IoU for natural...
-
LiWi: Layering in the Wild
Introduces LiWi-100k dataset via agent-orchestrated synthesis and a decomposition model with shadow-guided learning and boundary correction that claims state-of-the-art RGB L1 and Alpha IoU on natural images.
-
TripVVT: A Large-Scale Triplet Dataset and a Coarse-Mask Baseline for In-the-Wild Video Virtual Try-On
A new large-scale triplet dataset and diffusion transformer model using coarse human masks deliver improved video virtual try-on quality and generalization in challenging real-world conditions.
-
LiWi: Layering in the Wild
Presents LiWi-100k dataset generated via agent-driven decomposition and a model achieving SoTA on RGB L1 and Alpha IoU for natural image layering.
-
SIMON: Saliency-aware Integrative Multi-view Object-centric Neural Decoding
SIMON improves EEG-to-image retrieval by saliency-aware multi-view sampling, reaching 69.7% intra-subject and 19.6% inter-subject Top-1 accuracy on THINGS-EEG.
-
Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection
REFORM is a three-stage reasoning curriculum plus the ROM dataset that achieves state-of-the-art generalization on multimodal manipulation detection benchmarks.
-
SignNet-1M: Large-Scale Multilingual Sign Language Video Dataset with Downstream Benchmarks
The paper releases SignNet-1M, a 1M-scale augmented dataset for ASL, CSL and DGS with 3DGS and diffusion-based variations, plus benchmarks showing improved cross-shift generalization.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.