Search Results for author:
Found 29 papers, 10 papers with code
LightSim: Neural Lighting Simulation for Urban Scenes
Different outdoor illumination conditions drastically alter the appearance of urban scenes, and they can harm the performance of image-based robot perception systems if not seen during training.
Real-Time Neural Rasterization for Large Scenes
We propose a new method for realistic real-time novel-view synthesis (NVS) of large scenes.
Reconstructing Objects in-the-wild for Realistic Sensor Simulation
In this work, we present NeuSim, a novel approach that estimates accurate geometry and realistic appearance from sparse in-the-wild data captured at distance and at limited viewpoints.
CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulation
To tackle these issues, we present CADSim, which combines part-aware object-class priors via a small set of CAD models with differentiable rendering to automatically reconstruct vehicle geometry, including articulated wheels, with high-quality appearance.
Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
Learning world models can teach an agent how the world works in an unsupervised manner.
UniSim: A Neural Closed-Loop Sensor Simulator
Previously recorded driving logs provide a rich resource to build these new scenarios from, but for closed loop evaluation, we need to modify the sensor data based on the new scene configuration and the SDV's decisions, as actors might be added or removed and the trajectories of existing actors and the SDV will differ from the original log.
Towards Zero Domain Gap: A Comprehensive Study of Realistic LiDAR Simulation for Autonomy Testing
We leverage this setting to analyze what aspects of LiDAR simulation, such as pulse phenomena, scanning effects, and asset quality, affect the domain gap with respect to the autonomy system, including perception, prediction, and motion planning, and analyze how modifications to the simulated LiDAR influence each part.
Label-Guided Knowledge Distillation for Continual Semantic Segmentation on 2D Images and 3D Point Clouds
To address this issue, we propose a new label-guided knowledge distillation (LGKD) loss, where the old model output is expanded and transplanted (with the guidance of the ground truth label) to form a semantically appropriate class correspondence with the new model output.
Ranked #1 on
Continual Semantic Segmentation
on ScanNet
TANet: Thread-Aware Pretraining for Abstractive Conversational Summarization
Another is that applying the existing pre-trained models to this task is tricky because of the structural dependence within the conversation and its informal expression, etc.
RBGNet: Ray-based Grouping for 3D Object Detection
In order to learn better representations of object shape to enhance cluster features for predicting 3D boxes, we propose a ray-based feature grouping module, which aggregates the point-wise features on object surfaces using a group of determined rays uniformly emitted from cluster centers.
Ranked #13 on
3D Object Detection
on ScanNetV2
Efficient Few-Shot Object Detection via Knowledge Inheritance
Upon this baseline, we devise an initializer named knowledge inheritance (KI) to reliably initialize the novel weights for the box classifier, which effectively facilitates the knowledge transfer process and boosts the adaptation speed.
Assessment of Deep Learning-based Heart Rate Estimation using Remote Photoplethysmography under Different Illuminations
We evaluate the performance of three deep learning-based methods (Deepphys, rPPGNet, and Physnet) to that of four traditional methods (CHROM, GREEN, ICA, and POS) using two public datasets: the UBFC-rPPG dataset and the BH-rPPG dataset.
S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling
Constructing and animating humans is an important component for building virtual worlds in a wide variety of applications such as virtual reality or robotics testing in simulation.
Recovering and Simulating Pedestrians in the Wild
We then incorporate the reconstructed pedestrian assets bank in a realistic LiDAR simulation system by performing motion retargeting, and show that the simulated LiDAR data can be used to significantly reduce the amount of annotated real-world data required for visual perception tasks.
StyleDGPT: Stylized Response Generation with Pre-trained Language Models
Generating responses following a desired style has great potentials to extend applications of open-domain dialogue systems, yet is refrained by lacking of parallel data for training.
Open Domain Dialogue Generation with Latent Images
Thus, we propose learning a response generation model with both image-grounded dialogues and textual dialogues by assuming that the visual scene information at the time of a conversation can be represented by an image, and trying to recover the latent images of the textual dialogues through text-to-image generation techniques.
Context-Transformer: Tackling Object Confusion for Few-Shot Detection
Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors.
Dense RepPoints: Representing Visual Objects with Dense Point Sets
We present a new object representation, called Dense RepPoints, that utilizes a large set of points to describe an object at multiple levels, including both box level and pixel level.
Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System
The experiment results show that our method can significantly outperform the baseline methods and even achieve comparable results with the original teacher models, along with substantial speedup of model inference.
Learning Relationships for Multi-View 3D Object Recognition
Recognizing 3D object has attracted plenty of attention recently, and view-based methods have achieved best results until now.
Read, Attend and Comment: A Deep Architecture for Automatic NewsComment Generation
Automatic news comment generation is a new testbed for techniques of natural language generation.
On the Anomalous Generalization of GANs
Motivated by this observation, we discover two specific problems of GANs leading to anomalous generalization behaviour, which we refer to as the sample insufficiency and the pixel-wise combination.
Read, Attend and Comment: A Deep Architecture for Automatic News Comment Generation
Automatic news comment generation is a new testbed for techniques of natural language generation.
Low-Resource Response Generation with Template Prior
Since the paired data now is no longer enough to train a neural generation model, we consider leveraging the large scale of unpaired data that are much easier to obtain, and propose response generation with both paired and unpaired data.
RepPoints: Point Set Representation for Object Detection
They furthermore do not require the use of anchors to sample a space of bounding boxes.
Ranked #95 on
Object Detection
on COCO minival
NeuronBlocks: Building Your NLP DNN Models Like Playing Lego
Deep Neural Networks (DNN) have been widely employed in industry to address various Natural Language Processing (NLP) tasks.
Model Compression with Multi-Task Knowledge Distillation for Web-scale Question Answering System
Deep pre-training and fine-tuning models (like BERT, OpenAI GPT) have demonstrated excellent results in question answering areas.
Learning to Navigate for Fine-grained Classification
In consideration of intrinsic consistency between informativeness of the regions and their probability being ground-truth class, we design a novel training paradigm, which enables Navigator to detect most informative regions under the guidance from Teacher.
Ranked #42 on
Fine-Grained Image Classification
on FGVC Aircraft
Single Image Super-resolution via a Lightweight Residual Convolutional Neural Network
To tackle with the second problem, a lightweight CNN architecture which has carefully designed width, depth and skip connections was proposed.
