# Temporally Grounded Compositional Camera Motion Understanding via Geometric Knowledge Distillation

arXiv: https://arxiv.org/abs/2608.10932 · HTML: https://mlsanity.com/paper/2608.10932/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 35 of its 44 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [π3: Permutation-Equivariant Visual Geometry Learning](https://mlsanity.com/paper/2507.13347/) (2025)
- [ReCamMaster: Camera-Controlled Generative Rendering from A Single Video](https://mlsanity.com/paper/2503.11647/) (2025)
- [TransNet V2: An effective deep network architecture for fast shot transition detection](https://mlsanity.com/paper/2008.04838/) (2020)
- [ViPE: Video Pose Engine for 3D Geometric Perception](https://mlsanity.com/paper/2508.10934/) (2025)
- [Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors](https://mlsanity.com/paper/2505.24625/) (2025)
- [Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization](https://mlsanity.com/paper/2412.08376/) (2024)
- [SpatialVID: A Large-Scale Video Dataset with Spatial Annotations](https://mlsanity.com/paper/2509.09676/) (2025)
- [Towards Understanding Camera Motions in Any Video](https://mlsanity.com/paper/2504.15376/) (2025)
- [MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation](https://mlsanity.com/paper/2502.04299/) (2025)
- [CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation](https://mlsanity.com/paper/2505.15145/) (2025)
- [ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models](https://mlsanity.com/paper/2506.21356/) (2025)
- [A Survey on Video Temporal Grounding with Multimodal Large Language Model](https://mlsanity.com/paper/2508.10922/) (2025)
- [VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?](https://mlsanity.com/paper/2411.10979/) (2024)
- [RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation](https://mlsanity.com/paper/2510.02423/) (2025)
- [DROID-SLAM in the Wild](https://mlsanity.com/paper/2603.19076/) (2026)

## Built on by (most cited first, 1 of 1)

- [When Left Is Right? Camera-Motion Understanding beyond Screen](https://mlsanity.com/paper/2610.17242/) (2026)

## Abstract (arXiv)

Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation. Multimodal large language models (MLLMs) provide a natural interface for this task, but existing work typically assigns one or more labels to an entire clip. Such clip-level recognition overlooks two defining properties of real camera motion: it can change within a shot, and multiple movements can occur simultaneously. We therefore formulate camera-motion understanding as temporally grounded, compositional recognition, which requires a model to localize motion-consistent intervals and identify every movement active within each interval. We introduce CamChoreo, a benchmark of 4,229 real single-shot clips with expert-annotated temporal segments. Its annotations use a compact vocabulary of 20 direction-aware labels, and nearly half of the segments contain compound camera motion, with multiple movement primitives active simultaneously. Recognizing such fine-grained, compositional motion is hard for current MLLMs, whose visual encoders emphasize semantic content rather than the geometric evidence on which camera motion depends. Directly injecting features from a frozen 3D foundation model addresses this gap, but requires running the expensive geometry model on every input; we refer to this baseline as CamInject. We instead propose CamDistill, which distills the same geometric knowledge into lightweight camera tokens during training and removes the 3D model at inference. CamDistill matches the accuracy of direct feature injection without running the 3D teacher at inference. Together, CamChoreo and CamDistill advance camera-motion understanding from clip-level labeling to temporally grounded, compositional recognition. Project page: https://ddz16.github.io/cammotion.github.io/.