DreamTraj: Generating 6-DoF Object Trajectories by Reading Unrendered Video Diffusion Latents

• 类型：arxiv
• 标识：2608.00486
• 链接：https://arxiv.org/abs/2608.00486
• 主分类：multimodal
• 形态：method
• 被引：0
• 被引来源：Semantic Scholar
• S2被引：0
• 影响力被引：0
• TLDR：This work proposes DreamTraj, which predicts a 6-DoF object trajectory from a single RGB image and a task instruction, requiring no video, depth, or CAD model at inference, and is the first approach to directly decode object 6-DoF trajectories from intermediate video diffusion representations rather than generated pixels.
• 待LLM分类：否
• 标题中文：DreamTraj：通过读取未渲染的视频扩散潜在生成 6-DoF 物体轨迹
• TLDR中文：本文提出 DreamTraj，从单张 RGB 图像和任务指令预测物体 6-DoF 轨迹，推理时无需视频、深度或 CAD 模型，是首个直接从中间视频扩散表征（而非生成像素）解码物体 6-DoF 轨迹的方法
• 来源文件：
• /inbox/tom/_candidates/2026-08-04-agent-rag-longcontext-candidates.json
• [S2 enrich]