REVIEW 6 cited by
High-Quality Entity Segmentation
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
abstract
Dense image segmentation tasks e.g., semantic, panoptic) are useful for image editing, but existing methods can hardly generalize well in an in-the-wild setting where there are unrestricted image domains, classes, and image resolution and quality variations. Motivated by these observations, we construct a new entity segmentation dataset, with a strong focus on high-quality dense segmentation in the wild. The dataset contains images spanning diverse image domains and entities, along with plentiful high-resolution images and high-quality mask annotations for training and testing. Given the high-quality and -resolution nature of the dataset, we propose CropFormer which is designed to tackle the intractability of instance-level segmentation on high-resolution images. It improves mask prediction by fusing high-res image crops that provide more fine-grained image details and the full image. CropFormer is the first query-based Transformer architecture that can effectively fuse mask predictions from multiple image views, by learning queries that effectively associate the same entities across the full image and its crop. With CropFormer, we achieve a significant AP gain of $1.9$ on the challenging entity segmentation task. Furthermore, CropFormer consistently improves the accuracy of traditional segmentation tasks and datasets. The dataset and code will be released at http://luqi.info/entityv2.github.io/.
Forward citations
Cited by 6 Pith papers
-
Efficient Tracking and Understanding Object Transformations
FluxGraph detects object transformations reactively via SAM2's multi-mask disagreement, cutting TubeletGraph's inference cost by 3.3–10.7x with comparable tracking and state-graph quality.
-
O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning
An object-centric, training-free agentic pipeline that tracks object state changes and reasons over them with a vision-language model achieves strong video-level AUROC on Phys-AD, LiquidAD, and IPAD, while producing i...
-
CDIS: Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging
A training-free pipeline that tracks 2D masks frame-to-frame and associates them with 3D superpoints achieves 33.2 AP on ScanNet200 and 28.2 AP on ScanNet++, beating or matching prior zero-shot 3D instance segmentatio...
-
InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes
InstaScene combines Gaussian-based instance decomposition with generative completion to produce complete, scene-aligned 3D object models from cluttered scenes.
-
Splatting Physical Scenes: End-to-End Real-to-Sim from Imperfect Robot Data
A hybrid 3D Gaussian splatting plus explicit mesh representation, optimized end-to-end with differentiable rendering and physics, reconstructs objects and calibrates robot poses from imperfect real-world RGB trajectories.
-
OV-MAP: Open-Vocabulary Zero-Shot 3D Instance Segmentation Map for Robots
OV-MAP projects 2D masks into 3D and uses mesh-area voting to create zero-shot, open-vocabulary 3D instance segmentation maps.
Discussion (0). Sign in to comment.