21 citations · 54 across the 13 of their papers we have counts for
14 papers
Turbo4DGen: Ultra-Fast Acceleration for 4D Generation
Yuanbin Man, Ying Huang, Zhile Ren +1
4D generation, or dynamic 3D content generation, integrates spatial, temporal, and view dimensions to model realistic dynamic scenes, playing a foundational role in advancing world…
Apple Intelligence Foundation Language Models: Tech Report 2025
Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang +395
We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model opti…
Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference
Fred Hohman, Chaoqun Wang, Jinmook Lee +7
On-device machine learning (ML) moves computation from the cloud to personal devices, protecting user privacy and enabling intelligent user experiences. However, fitting models on…
UPSCALE: Unconstrained Channel Pruning
Alvin Wan, Hanxiang Hao, Kaushik Patnaik +5
As neural networks grow in size and complexity, inference speeds decline. To combat this, one of the most effective compression techniques -- channel pruning -- removes channels fr…
AutoFocusFormer: Image Segmentation off the Grid
Chen Ziwen, Kaushik Patnaik, Shuangfei Zhai +5
Real world images often have highly imbalanced content density. Some areas are very uniform, e.g., large patches of blue sky, while other areas are scattered with many small object…
Generative Multiplane Images: Making a 2D GAN 3D-Aware
Xiaoming Zhao, Fangchang Ma, David Güera +3
What is really needed to make an existing 2D GAN 3D-aware? To answer this question, we modify a classical GAN, i.e., StyleGANv2, as little as possible. We find that only two modifi…
FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction
Zhenpei Yang, Zhile Ren, Miguel Angel Bautista +3
Reconstructing an accurate 3D object model from a few image observations remains a challenging problem in computer vision. State-of-the-art approaches typically assume accurate cam…
VideoPose: Estimating 6D object pose from videos
Apoorva Beedu, Zhile Ren, Varun Agrawal +1
We introduce a simple yet effective algorithm that uses convolutional neural networks to directly estimate object poses from videos. Our approach leverages the temporal information…
MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions
Zhenpei Yang, Zhile Ren, Qi Shan +1
Deep learning has made significant impacts on multi-view stereo systems. State-of-the-art approaches typically involve building a cost volume, followed by multiple 3D convolution o…
Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Views
Vincent Cartillier, Zhile Ren, Neha Jain +3
We study the task of semantic mapping - specifically, an embodied agent (a robot or an egocentric AI assistant) is given a tour of a new environment and asked to build an allocentr…
Clouds of Oriented Gradients for 3D Detection of Objects, Surfaces, and Indoor Scene Layouts
Zhile Ren, Erik B. Sudderth
We develop new representations and algorithms for three-dimensional (3D) object detection and spatial layout prediction in cluttered indoor scenes. We first propose a clouds of ori…
Embodied Visual Recognition
Jianwei Yang, Zhile Ren, Mingze Xu +4
Passive visual systems typically fail to recognize objects in the amodal setting where they are heavily occluded. In contrast, humans and other embodied agents have the ability to…
3D Scene Reconstruction with Multi-layer Depth and Epipolar Transformers
Daeyun Shin, Zhile Ren, Erik B. Sudderth +1
We tackle the problem of automatically reconstructing a complete 3D model of a scene from a single RGB image. This challenging task requires inferring the shape of both visible and…
A Fusion Approach for Multi-Frame Optical Flow Estimation
Zhile Ren, Orazio Gallo, Deqing Sun +3
To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account. While elegant and appealing, the idea of using more than two frames has…