Xianda Guo

I am interested in computer vision and autonomous driving. My current research focuses on:

Email  /  Google Scholar  /  GitHub

*Equal contribution    ^†Project leader/Corresponding author.

Selected Papers [Full List]

OpenStereo includes training and inference codes of more than 10 network models, making it, to our knowledge, the most complete stereo matching toolbox available.

We present LightStereo, a cutting-edge stereo-matching network crafted to accelerate the matching process.

We introduce a novel synthetic dataset that complements existing data by adding variability in baselines, camera angles, and scene types. We extensively evaluate the zero-shot capabilities of our model on five public datasets, showcasing its impressive ability to generalize to new, unseen data.

We present StereoCarla, a high-fidelity synthetic stereo dataset specifically designed for autonomous driving scenarios. Built on the CARLA simulator, StereoCarla incorporates a wide range of camera configurations, including diverse baselines, viewpoints, and sensor placements as well as varied environmental conditions such as lighting changes, weather effects, and road geometries.

We propose StereoFactory, a coarse-to-fine evolutionary framework for adaptive model merging. Stage~1 employs a genetic algorithm to search the combinatorial space of model subsets, determining which models should participate. Stage~2 addresses module-level knowledge specialization (different functional modules exhibit distinct preferences for knowledge sources) through CMA-ES optimization of architecture-adaptive routing over the selected task vectors, with optional module-level scaling.

We present Humanoid-OmniOcc, a large-scale panoramic stereo-based occupancy dataset tailored for humanoid robots. And we further propose Humanoid Surround Stereo-guided Occupancy model that exploits robust depth priors for accurate 2D-to-3D lifting.

In light of the recent successes achieved by Vision Transformers (ViTs), we propose MonoViT, a brand-new framework combining the global reasoning enabled by ViT models with the flexibility of self-supervised monocular depth estimation.

This paper proposes a Joint Convolutional Attention and Transformer block (JCAT), which deeply couples the convolutional attention layer and Vision Transformer into one block, as the basic unit to construct our depth completion model in a pyramidal structure.

We propose DiffusionDepth, a new approach that reformulates monocular depth estimation as a denoising diffusion process. It learns an iterative denoising process to `denoise' random depth distribution into a depth map with the guidance of monocular visual conditions.

GenAD casts end-to-end autonomous driving as a generative modeling problem.

We introduce SURDS, a benchmark specifically designed to evaluate the spatial understanding capabilities of multimodal large language models (MLLMs) in autonomous driving.

Website Template