# GimbalDiffusion: Gravity-Aware Camera Control for Video Generation

Source: [GimbalDiffusion: Gravity-Aware Camera Control for Video Generation](<https://www.sota2.com/research/paper/693a501e6cfd488761a54b29>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-08-05T05:00:12.726Z

Authors: Fr\\'ed\\'eric Fortier-Chouinard, Yannick Hold-Geoffroy, Valentin Deschaintre, Matheus Gadelha, Jean-Fran\\c{c}ois Lalonde

Published: 2025-12-09T20:54:35.000Z

## Abstract

Recent progress in text-to-video generation has achieved remarkable realism, yet fine-grained control over camera motion and orientation remains elusive, especially with extreme trajectories (e.g., a 180-degree turnaround, or looking directly up or down). Existing approaches typically encode camera trajectories using relative or ambiguous representations, limiting precise geometric control and offering limited support for large rotations. We introduce GimbalDiffusion, a framework that enables camera control grounded in physical-world coordinates, using gravity as a global reference. Instead of describing motion relative to previous frames, our method defines camera trajectories in an absolute coordinate system, allowing accurate, interpretable control over camera parameters. Using panoramic 360-degree videos for training, we cover the full sphere of possible viewpoints, including combinations of extreme pitch and roll that are out-of-distribution of conventional video data. To improve camera control, we introduce null-pitch conditioning, a strategy that prevents the model from overriding camera specifications in the presence of conflicting prompt content (e.g., generating grass while the camera points toward the sky). Finally, we propose new benchmarks to evaluate gravity-aware camera-controlled video generation, assessing models' ability to generate extreme camera angles and quantify their input prompt entanglement.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Camera-controlled video generation on SpatialVID extreme](<https://www.sota2.com/research/sota/camera-controlled-video-generation-on-spatialvid-extreme.md>): Camera-controlled Video Generation; SpatialVID extreme; PitchErr (abs): 23.79.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.09112>)

[PDF](<https://arxiv.org/pdf/2512.09112.pdf>)