CVOct 23, 2024

FreeVS: Generative View Synthesis on Free Driving Trajectory

arXiv:2410.18079v151 citationsh-index: 23ICLR
Originality Incremental advance
AI Analysis

This work addresses the challenge of generating realistic views for autonomous driving applications, enabling synthesis on arbitrary trajectories, though it is incremental in improving over reconstruction-based methods.

The authors tackled the problem of novel view synthesis in driving scenes, where existing methods degrade on viewpoints outside recorded trajectories, and proposed FreeVS, a fully generative approach that synthesizes camera views on free new trajectories with strong image synthesis performance on both recorded and novel trajectories.

Existing reconstruction-based novel view synthesis methods for driving scenes focus on synthesizing camera views along the recorded trajectory of the ego vehicle. Their image rendering performance will severely degrade on viewpoints falling out of the recorded trajectory, where camera rays are untrained. We propose FreeVS, a novel fully generative approach that can synthesize camera views on free new trajectories in real driving scenes. To control the generation results to be 3D consistent with the real scenes and accurate in viewpoint pose, we propose the pseudo-image representation of view priors to control the generation process. Viewpoint transformation simulation is applied on pseudo-images to simulate camera movement in each direction. Once trained, FreeVS can be applied to any validation sequences without reconstruction process and synthesis views on novel trajectories. Moreover, we propose two new challenging benchmarks tailored to driving scenes, which are novel camera synthesis and novel trajectory synthesis, emphasizing the freedom of viewpoints. Given that no ground truth images are available on novel trajectories, we also propose to evaluate the consistency of images synthesized on novel trajectories with 3D perception models. Experiments on the Waymo Open Dataset show that FreeVS has a strong image synthesis performance on both the recorded trajectories and novel trajectories. Project Page: https://freevs24.github.io/

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes