paper-with-me

홈 › Papers

SPATIALALIGN: Aligning Dynamic Spatial Relationships in Video Generation

2026-02-26 · Fengming Liu, Tat-Jen Cham, Chuanxia Zheng arxiv

Most text-to-video (T2V) generators prioritize aesthetic quality, but often ignoring the spatial constraints in the generated videos. In this work, we present SPATIALALIGN, a self-improvement framework that enhances T2V models capabilities to depict Dynamic Spatial Relationships (DSR) specified in text prompts. We present a zeroth-order regularized Direct Preference Optimization (DPO) to fine-tune T2V models towards better alignment with DSR. Specifically, we design DSR-SCORE, a geometry-based metric that quantitatively measures the alignment between generated videos and the specified DSRs in prompts, which is a step forward from prior works that rely on VLM for evaluation. We also conduct a dataset of text-video pairs with diverse DSRs to facilitate the study. Extensive experiments demonstrate that our fine-tuned model significantly out performs the baseline in spatial relationships. The code will be released in Link. Project page: https://fengming001ntu.github.io/SpatialAlign/

📄 PDF Abstract BibTeX arXiv:2602.22745

Code (0)

등록된 구현이 없습니다.

Tasks

Video Generation

Similar Papers 제목 키워드 기반

Spatial-Temporal Transformer for Dynamic Scene Graph Generation

2021-07-26 · ICCV 2021 10 · Yuren Cong, Wentong Liao, Hanno Ackermann, Bodo Rosenhahn 외

Dynamic scene graph generation aims at generating a scene graph of the given video. Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects …

DecoderScene Graph GenerationVideo UnderstandingVideo Visual Relation Detection+1

DVLTA-VQA: Decoupled Vision-Language Modeling with Text-Guided Adaptation for Blind Video Quality Assessment

2025-04-16 · Li Yu, Situo Wang, Wei Zhou, Moncef Gabbouj

Inspired by the dual-stream theory of the human visual system (HVS) - where the ventral stream is responsible for object recognition and detail analysis, while the dorsal stream focuses on spatial relationships and motio…

Language ModelingLanguage ModellingObject RecognitionVideo Quality Assessment+1

SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models

2024-12-10 · Arijit Ray, Jiafei Duan, Ellis Brown, Reuben Tan 외

Reasoning about motion and space is a fundamental cognitive capability that is required by multiple real-world applications. While many studies highlight that large multimodal language models (MLMs) struggle to reason ab…

Action RecognitionSpatial Reasoning

ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding

2025-11-25 · Byeongjun Park, Byung-Hoon Kim, Hyungjin Chung, Jong Chul Ye arxiv

We present ReDirector, a novel camera-controlled video retake generation method for dynamically captured variable-length videos. In particular, we rectify a common misuse of RoPE in previous works by aligning the spatiot…

Object Localization

VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models

2025-04-17 · Haojian Huang, Haodong Chen, Shengqiong Wu, Meng Luo 외

Large Video Models (LVMs) built upon Large Language Models (LLMs) have shown promise in video understanding but often suffer from misalignment with human intuition and video hallucination issues. To address these challen…

HallucinationVideo Understanding