AIConfPaper
← Search

Guocheng Qian

17 accepted papers

2025

AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers

Sherwin Bahmani, Ivan Skorokhodov, Guocheng Qian, Aliaksandr Siarohin, Willi Menapace, Andrea Tagliasacchi +2
CVPR 2025poster

Numerous works have recently integrated 3D camera control into foundational text-to-video models, but the resulting camera control is often imprecise, and video generation quality suffers. In this work, we analyze camera motion from a first principles perspective, uncovering insights that enable pre…

Cited by 10Source ↗PDF ↗Scholar ↗
2025

I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models

Zhenxing Mi, Kuan-Chieh Wang, Guocheng Qian, Hanrong Ye, Runtao Liu, Sergey Tulyakov +2
ICML 2025poster

This paper presents ThinkDiff, a novel alignment paradigm that empowers text-to-image diffusion models with multimodal in-context understanding and reasoning capabilities by integrating the strengths of vision-language models (VLMs). Existing multimodal diffusion finetuning methods largely focus on…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Omni-ID: Holistic Identity Representation Designed for Generative Tasks

Guocheng Qian, Kuan-Chieh Wang, Or Patashnik, Negin Heravi, Daniil Ostashev, Sergey Tulyakov +2
CVPR 2025poster

We introduce Omni-ID, a novel facial representation designed specifically for generative tasks. Omni-ID encodes holistic information about an individual's appearance across diverse expressions and poses within a fixed-size representation. It consolidates information from a varied number of unstructu…

Cited by 3Source ↗PDF ↗Scholar ↗
2025

Preventing Shortcuts in Adapter Training via Providing the Shortcuts

Anujraaj Goyal, Guocheng Qian, Huseyin Coskun, Aarush Gupta, Himmy Tam, Daniil Ostashev +5
NeurIPS 2025poster

Adapter-based training has emerged as a key mechanism for extending the capabilities of powerful foundation image generators, enabling personalized and stylized text-to-image synthesis. These adapters are typically trained to capture a specific target attribute, such as subject identity, using singl…

Cited by 0Source ↗Scholar ↗
2025

VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control

Sherwin Bahmani, Ivan Skorokhodov, Aliaksandr Siarohin, Willi Menapace, Guocheng Qian, Michael Vasilkovsky +6
ICLR 2025poster

Modern text-to-video synthesis models demonstrate coherent, photorealistic generation of complex videos from a text description. However, most existing models lack fine-grained control over camera movement, which is critical for downstream applications related to content creation, visual effects, an…

Cited by 38Source ↗PDF ↗Scholar ↗
2025

Wonderland: Navigating 3D Scenes from a Single Image

Hanwen Liang, Junli Cao, Vidit Goel, Guocheng Qian, Sergei Korolev, Demetri Terzopoulos +3
CVPR 2025poster

This paper addresses a challenging question: how can we efficiently create high-quality, wide-scope 3D scenes from a single arbitrary image?Existing methods face several constraints, such as requiring multi-view data, time-consuming per-scene optimization, low visual quality, and distorted reconstru…

Cited by 12Source ↗PDF ↗Scholar ↗
2024

Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning

Chen Zhao, Shuming Liu, Karttikeya Mangalam, Guocheng Qian, Fatimah Zohra, Abdulmohsen Alghannam +2
CVPR 2024poster

Large pretrained models are increasingly crucial in modern computer vision tasks. These models are typically used in downstream tasks by end-to-end finetuning which is highly memory-intensive for tasks with high-resolution data e.g. video understanding small object detection and point cloud analysis…

Cited by 4Source ↗PDF ↗code ↗Scholar ↗
2024

FastPCI: Motion-Structure Guided Fast Point Cloud Frame Interpolation

tianyu zhang, Guocheng Qian, Jin Xie*, Jian Yang
ECCV 2024poster

"Point cloud frame interpolation is a challenging task that involves accurate scene flow estimation across frames and maintaining the geometry structure. Prevailing techniques often rely on pre-trained motion estimators or intensive testing-time optimization, resulting in compromised interpolation a…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

GES : Generalized Exponential Splatting for Efficient Radiance Field Rendering

Abdullah Hamdi, Luke Melas-Kyriazi, Jinjie Mai, Guocheng Qian, Ruoshi Liu, Carl Vondrick +2
CVPR 2024poster

Advancements in 3D Gaussian Splatting have significantly accelerated 3D reconstruction and generation. However it may require a large number of Gaussians which creates a substantial memory footprint. This paper introduces GES (Generalized Exponential Splatting) a novel representation that employs Ge…

Cited by 44Source ↗PDF ↗code ↗Scholar ↗
2024

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors

Guocheng Qian, Jinjie Mai, Abdullah Hamdi, Jian Ren, Aliaksandr Siarohin, Bing Li +5
ICLR 2024poster

We present ``Magic123'', a two-stage coarse-to-fine approach for high-quality, textured 3D mesh generation from a single image in the wild using *both 2D and 3D priors*. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-effic…

Cited by 356Source ↗PDF ↗code ↗Scholar ↗
2024

SPAD: Spatially Aware Multi-View Diffusers

Yash Kant, Aliaksandr Siarohin, Ziyi Wu, Michael Vasilkovsky, Guocheng Qian, Jian Ren +4
CVPR 2024poster

We present SPAD a novel approach for creating consistent multi-view images from text prompts or single images. To enable multi-view generation we repurpose a pretrained 2D diffusion model by extending its self-attention layers with cross-view interactions and fine-tune it on a high quality subset of…

Cited by 34Source ↗PDF ↗Scholar ↗
2024

TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks

Jinjie Mai*, Wenxuan Zhu, Sara Rojas, Jesus Zarzar, Abdullah Hamdi, Guocheng Qian +3
ECCV 2024poster

"Neural radiance fields (NeRFs) generally require many images with accurate poses for accurate novel view synthesis, which does not reflect realistic setups where views can be sparse and poses can be noisy. Previous solutions for learning NeRFs with sparse views and noisy poses only consider local g…

Cited by 7Source ↗PDF ↗code ↗Scholar ↗
2023

Exploring Open-Vocabulary Semantic Segmentation from CLIP Vision Encoder Distillation Only

Jun Chen, Deyao Zhu, Guocheng Qian, Bernard Ghanem, Zhicheng Yan, Chenchen Zhu +3
ICCV 2023poster

Semantic segmentation is a crucial task in computer vision that involves segmenting images into semantically meaningful regions at the pixel level. However, existing approaches often rely on expensive human annotations as supervision for model training, limiting their scalability to large, unlabeled…

Cited by 33PDF ↗code ↗Scholar ↗
2022

PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

Guocheng Qian, Yuchen Li, Houwen Peng, Jinjie Mai, Hasan Abed Al Kader Hammoud, Mohamed Elhoseiny +1
NeurIPS 2022accept

PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks such as PointMLP and Point Transformer, we find that a large portion of the performance gain is due to improved training str…

Cited by 776Source ↗PDF ↗code ↗Scholar ↗
2021

ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning

Guocheng Qian, Hasan Abed Al Kader Hammoud, Guohao Li, Ali Thabet, Bernard Ghanem
NeurIPS 2021spotlight

Access to 3D point cloud representations has been widely facilitated by LiDAR sensors embedded in various mobile devices. This has led to an emerging need for fast and accurate point cloud processing techniques. In this paper, we revisit and dive deeper into PointNet++, one of the most influential y…

Cited by 97Source ↗PDF ↗code ↗Scholar ↗
2021

PU-GCN: Point Cloud Upsampling Using Graph Convolutional Networks

Guocheng Qian, Abdulellah Abualshour, Guohao Li, Ali Thabet, Bernard Ghanem
CVPR 2021poster

The effectiveness of learning-based point cloud upsampling pipelines heavily relies on the upsampling modules and feature extractors used therein. For the point upsampling module, we propose a novel model called NodeShuffle, which uses a Graph Convolutional Network (GCN) to better encode local point…

Cited by 271PDF ↗code ↗Scholar ↗
2020

SGAS: Sequential Greedy Architecture Search

Guohao Li, Guocheng Qian, Itzel C. Delgadillo, Matthias Muller, Ali Thabet, Bernard Ghanem
CVPR 2020poster

Architecture design has become a crucial component of successful deep learning. Recent progress in automatic neural architecture search (NAS) shows a lot of promise. However, discovered architectures often fail to generalize in the final evaluation. Architectures with a higher validation accuracy du…

Cited by 267PDF ↗Scholar ↗