ConfCtrl: Enabling Precise Camera Control in Video Diffusion via Confidence-Aware Interpolation

TL;DR

ConfCtrl introduces a confidence-aware interpolation method for diffusion models to synthesize novel views from two images, accurately reconstructing unseen regions while adhering to prescribed camera trajectories.

Contribution

The paper presents ConfCtrl, a novel framework that combines confidence-weighted point cloud projections with a Kalman-inspired update to improve view synthesis accuracy.

Findings

Produces geometrically consistent novel views

Effectively reconstructs occluded regions

Maintains stable camera trajectories during synthesis

Abstract

We address the challenge of novel view synthesis from only two input images under large viewpoint changes. Existing regression-based methods lack the capacity to reconstruct unseen regions, while camera-guided diffusion models often deviate from intended trajectories due to noisy point cloud projections or insufficient conditioning from camera poses. To address these issues, we propose ConfCtrl, a confidence-aware video interpolation framework that enables diffusion models to follow prescribed camera poses while completing unseen regions. ConfCtrl initializes the diffusion process by combining a confidence-weighted projected point cloud latent with noise as the conditioning input. It then applies a Kalman-inspired predict-update mechanism, treating the projected point cloud as a noisy measurement and using learned residual corrections to balance pose-driven predictions with noisy geometric observations. This allows the model to rely on reliable projections while down-weighting uncertain regions, yielding stable, geometry-aware generation. Experiments on multiple datasets show that ConfCtrl produces geometrically consistent and visually plausible novel views, effectively reconstructing occluded regions under large viewpoint changes.