Research

My full publication list is available on Google Scholar.

Amazon Nova
The Amazon Nova Family of Generative Models

Amazon AGI

We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence with industry-leading price performance. Amazon Nova Reel is our advanced video generation model, offering high-quality outputs, customization, and motion control. Nova Canvas enables professional-grade image generation with rich customization tools. Our multimodal models Nova Pro, Lite, and Micro offer cutting-edge capabilities across text, image, video, and document processing.

Amazon Nova
Diffusion Soup: Model Merging for Text-to-Image Diffusion Models (ECCV 2024)

Benjamin Biggs*, Arjun Seshadri*, Yang Zou, Achin Jain, Aditya Golatkar, Yusheng Xie, Alessandro Achille, Ashwin Swaminathan, Stefano Soatto

We present Diffusion Soup, a compartmentalization method for Text-to-Image Generation that averages the weights of diffusion models trained on sharded data. By construction, our approach enables training-free continual learning and unlearning with no additional memory or inference costs. Our method achieves up to 30% improvement vs. a paragon model, and has applications in anti-memorization and zero-shot style mixing.

Amazon Titan Image Generator
Amazon Titan Image Generator

AWS Bedrock

Amazon Titan Image Generator is a foundational generative model which enables content creators to generate and edit high-quality images using natural language prompts. The model allows users to create, modify, and repurpose images, and supports responsible AI use with built-in safeguards and invisible watermarking.

3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data (NeurIPS 2020, Spotlight - Top 3%)

Benjamin Biggs, Sébastien Ehrhadt, Hanbyul Joo, Benjamin Graham, Andrea Vedaldi and David Novotny

We tackle the problem of obtaining dense 3D human reconstructions from single and partially occluded views. In such cases, the visual evidence is usually insufficient to identify a 3D reconstruction uniquely, so we recover a set of plausible and reconstructions, consistent with the input image. We train using a best-of-M loss, to which we add flexibility with a novel quantization scheme based on normalizing flows.

Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop (ECCV 2020)

Benjamin Biggs, Oliver Boyne, James Charles, Andrew Fitzgibbon and Roberto Cipolla

We introduce a fully automatic, end-to-end system for 3D dog reconstruction trained using only weak 2D supervision. We use SMBLD, a new 3D deformable template model which includes a detailed shape prior learnt training using expectation maximization. We also release StanfordExtra: the largest dataset of 2D keypoints and segmentations for an animal category.

Creatures Great and SMAL: Recovering the Shape and Motion of Animals from Video (ACCV 2018, Oral - Top 5%)

Benjamin Biggs, Thomas Roddick, Andrew Fitzgibbon and Roberto Cipolla

A system to recover the 3D shape and motion of a wide variety of quadruped animals from video. We overcome the limited availability of animal motion capture data and ensure generalizability to real-world sequences by training on synthetic silhouettes. We apply our method on manually-segmented and automatically-segmented monocular animal videos and require no other form of user intervention.

Shape of You
Shape of You: Precise 3D Shape Estimations for Diverse Body Types (CVPR-W 2023, Oral)

Rohan Sakar, Achal Dave, Gerard Medioni and Benjamin Biggs

We improve 3D body shape estimation for diverse body types. While existing methods successfully estimate 3D pose, reliably estimating precise shape remains challenging. To address this gap, we propose new loss functions and a test-time optimization routine that can be readily integrated into parametric 3D human reconstruction pipelines.

Shape of You
On the Road to Large-Scale 3D Monocular Scene Reconstruction Using Deep Implicit Functions (ICCV-W 2021)

Thomas Roddick, Benjamin Biggs, Daniel Olmeda Reino and Roberto Cipolla

We propose deep implicit functions to reconstruct large-scale driving scenes. To avoid requiring watertight meshes for training, we instead use LiDAR to approximate ground truth occupancy labels. We evaluate on a real-world autonomous driving dataset and show incorporating geometric priors improves reconstruction quality.

Other Research

Benjamin Biggs - PhD Thesis
PhD Thesis - Benjamin Biggs

Supervisors: Roberto Cipolla & Andrew Fitzgibbon

This thesis focuses on designing methods for animal reconstruction, making use of 3D morphable models. Topics covered include: training 3D animal reconstruction algorithms with synthetic silhouette data, refining 3D shape priors in-the-loop and handling ambiguous input images.

Virtual Try-On with Outfit Layer Mask
Virtual Try-On with Outfit Layer Mask

Benjamin Biggs, Philip Pinette, Charu Kothari, Caitlin Cagampan, Achal Dave, Scott Sun and Gerard Medioni

Our virtual try-on method generates a realistic digital model of a person based on an image and seamlessly applies clothing to it. By analyzing both the body and clothing images, we create a layer mask that determines how each pixel should be rendered, based on which part of the body it belongs to. The result is a highly accurate virtual try-on experience, suitable for rendering full outfits on a selected body. This was built as part of the Amazon Style project, an ML-powered physical fashion store.

Benjamin Biggs - PhD Thesis
StanfordExtra

Benjamin Biggs, Oliver Boyne, Andrew Fitzgibbon and Roberto Cipolla

12k labelled instances of dogs in-the-wild with 2D keypoint and segmentations.

RodentNet

Benjamin Biggs, Andrew Fitzgibbon and Roberto Cipolla

Behaviour and key point predictions at ~15fps by a deep learning architecture we refer to as RodentNet. Results shown on validation sequences from the SCORHE dataset.

Kinect Gowning Application

Benjamin Biggs, Patrick Hyett and Abhir Bhalerao

Computer vision application for verifying regulatory gowning procedures in collaboration with GlaxoSmithKline. Won departmental award for best third year dissertation at the University of Warwick.