ScanRefer
PulseAugur coverage of ScanRefer — every cluster mentioning ScanRefer across labs, papers, and developer communities, ranked by signal.
1 天有情绪数据
-
SceneGraphGrounder 使用3D场景图进行零样本视觉定位
研究人员推出 SceneGraphGrounder，一个专为零样本3D视觉定位设计的新型框架。该方法通过将任务转化为结构化场景图匹配问题，解决了在非结构化环境中利用自然语言定位对象这一挑战。该系统从2D视图中重建3D场景图，编码空间和语义关系，然后将查询图与该场景图对齐，以实现一致且可解释的推理。在ScanRefer基准测试上的实验显示出具有竞争力的结果，并且该框架已在移动机器人上进行了现实世界应用的验证。
-
New frameworks MCM-VG and DEGround advance zero-shot 3D visual grounding
Researchers have developed two new frameworks, DEGround and MCM-VG, to improve ego-centric 3D visual grounding, a key task for embodied intelligence. DEGround utilizes a homogeneous pipeline that shares object represent…
-
Chat-Scene++ advances 3D LLM scene understanding with context-rich object identification
Researchers have introduced Chat-Scene++, a novel framework designed to enhance multi-modal large language models (MLLMs) for 3D scene understanding. This approach structures 3D scenes as sequences of objects, incorpora…