Boosting Text-Driven Video Segmentation via Geometry-Aware Distillation

• URL: http://arxiv.org/abs/2606.24464v1
• Date: Tue, 23 Jun 2026 11:57:08 GMT
• Title: Boosting Text-Driven Video Segmentation via Geometry-Aware Distillation
• Abstract summary: Text-driven Referring Video Object (RVOS) aims to locate and segment target objects in videos given natural language.<n>Existing models are typically trained on 2D image or video datasets with naive segmentation losses.<n>We propose Geometry-enhanced Language-guided Video segmentation (GeoLaV) to enhance text-driven video segmentation.
• Score: 17.44364775825169
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Text-driven Referring Video Object Segmentation (RVOS) aims to locate and segment target objects in videos given natural language. However, existing models are typically trained on 2D image or video datasets with naive segmentation losses, which overlooks the geometric consistency across frames and leads to weak spatial understanding. In this paper, we propose Geometry-enhanced Language-guided Video segmentation (GeoLaV), a two-stage framework that distills 3D geometric knowledge from images to enhance text-driven video segmentation. In the first stage, we perform monocular geometry pretraining with monocular novel-view synthesis, enabling the model to acquire geometry-consistent visual representations via spatial alignment on large-scale single-image datasets. In the second stage, we introduce geometry-aware distillation and fine-tune the model on video segmentation datasets, transferring 3D structural knowledge from a general 3D prior model. This process reinforces 3D awareness and improves both spatiotemporal coherence and language grounding in segmentation. Extensive experiments show that our method using only image segmentation data already provides notable zero-shot generalization in RVOS. When combined with geometry-aware distillation for fine-tuning on videos, our method achieves state-of-the-art performance across multiple RVOS benchmarks. The code is available at https://github.com/Tony1882880/GeoLaV.

Related papers

• ScaleVid: Geometry-Aware Video Object Scaling with Mesh-Free Inference [13.10996719828907]
  Geometry-aware video object scaling aims to anisotropically resize the object along object-centric axes while preserving geometric plausibility, temporal coherence, and background consistency.<n>We present a two-stage training framework that decouples geometry-aware foreground transformation from background preservation and realistic video composition.<n>In both stages, geometrically perturbed pseudo-sources are constructed from real videos, while the original complete videos are retained as reconstruction targets.
  arXiv  Detail & Related papers  (2026-08-12T16:28:26Z)
• Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context [33.99324999592141]
  Scene-consistent video generation aims to create videos that explore 3D scenes based on a camera trajectory.<n>Previous methods rely on video generation models with external memory for consistency.<n>We introduce geometry-as-context" to overcome these limitations.
  arXiv  Detail & Related papers  (2026-02-25T14:09:03Z)
• Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video [76.32954467706581]
  We propose SAGE, a framework for Scalable Adaptation of GEometric foundation models from raw video streams.<n>We use a hierarchical mining pipeline to transform videos into training trajectories and hybrid supervision.<n>Experiments show that SAGE significantly enhances zero-shot generalization, reducing Chamfer Distance by 20-42% on unseen benchmarks.
  arXiv  Detail & Related papers  (2026-02-08T09:53:21Z)
• Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models [79.18306680174011]
  DSR Suite bridges gap across aspects of dataset, benchmark and model.<n>We propose an automated pipeline that generates multiple-choice question-answer pairs from in-the-wild videos for DSR.<n>The pipeline extracts rich geometric and motion information, including camera poses, local point clouds, object masks, orientations, and 3D trajectories.
  arXiv  Detail & Related papers  (2025-12-23T17:56:36Z)
• GLaD: Geometric Latent Distillation for Vision-Language-Action Models [106.53332923530245]
  We introduce GLaD, a geometry-aware Vision-Language-Action (VLA) framework that incorporates 3D geometric priors during pretraining through knowledge distillation.<n>GLaD achieves 94.1% average success rate across four LIBERO task suites, outperforming UniVLA (92.5%) which uses identical pretraining data.
  arXiv  Detail & Related papers  (2025-12-10T13:07:27Z)
• Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling [29.723534231743038]
  We propose Geometry Forcing to bridge the gap between video diffusion models and the underlying 3D nature of the physical world.<n>Our key insight is to guide the model's intermediate representations toward geometry-aware structure by aligning them with features from a pretrained geometric foundation model.<n>We evaluate Geometry Forcing on both camera view-conditioned and action-conditioned video generation tasks.
  arXiv  Detail & Related papers  (2025-07-10T17:55:08Z)
• 3D Part Segmentation via Geometric Aggregation of 2D Visual Features [57.20161517451834]
  Supervised 3D part segmentation models are tailored for a fixed set of objects and parts, limiting their transferability to open-set, real-world scenarios.<n>Recent works have explored vision-language models (VLMs) as a promising alternative, using multi-view rendering and textual prompting to identify object parts.<n>To address these limitations, we propose COPS, a COmprehensive model for Parts that blends semantics extracted from visual concepts and 3D geometry to effectively identify object parts.
  arXiv  Detail & Related papers  (2024-12-05T15:27:58Z)
• Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding [11.416392706435415]
  Zero-shot 3D point cloud understanding can be achieved via 2D Vision-Language Models (VLMs) Existing strategies directly map Vision-Language Models from 2D pixels of rendered or captured views to 3D points, overlooking the inherent and expressible point cloud geometric structure. We introduce the first training-free aggregation technique that leverages the point cloud's 3D geometric structure to improve the quality of the transferred Vision-Language Models.
  arXiv  Detail & Related papers  (2023-12-04T12:30:07Z)
• AutoDecoding Latent 3D Diffusion Models [95.7279510847827]
  We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space. We then identify the appropriate intermediate volumetric latent space, and introduce robust normalization and de-normalization operations.
  arXiv  Detail & Related papers  (2023-07-07T17:59:14Z)
• MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation [91.6658845016214]
  We propose to utilize self-supervised techniques in the 2D domain for fine-grained 3D shape segmentation tasks. We render a 3D shape from multiple views, and set up a dense correspondence learning task within the contrastive learning framework. As a result, the learned 2D representations are view-invariant and geometrically consistent.
  arXiv  Detail & Related papers  (2022-08-18T00:48:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.