{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bird-s-eye-view-scene-graph-for-vision","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","arxiv_id":"2308.04758","date":"2023-08-09","proceeding":"ICCV 2023 1","authors":["Rui Liu","Xiaohan Wang","Wenguan Wang","Yi Yang"],"abstract":"Vision-language navigation (VLN), which entails an agent to navigate 3D environments following human instructions, has shown great advances. However, current agents are built upon panoramic observations, which hinders their ability to perceive 3D scene geometry and easily leads to ambiguous selection of panoramic view. To address these limitations, we present a BEV Scene Graph (BSG), which leverages multi-step BEV representations to encode scene layouts and geometric cues of indoor environment under the supervision of 3D detection. During navigation, BSG builds a local BEV representation at each step and maintains a BEV-based global scene map, which stores and organizes all the online collected local BEV representations according to their topological relations. Based on BSG, the agent predicts a local BEV grid-level decision score and a global graph-level decision score, combined with a sub-view selection score on panoramic views, for more accurate action prediction. Our approach significantly outperforms state-of-the-art methods on REVERIE, R2R, and R4R, showing the potential of BEV perception in VLN.","url_abs":"https://arxiv.org/abs/2308.04758v2","url_pdf":"https://arxiv.org/pdf/2308.04758v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bird-s-eye-view-scene-graph-for-vision","repo_url":"https://github.com/defaultrui/bev-scene-graph","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"vision-language-navigation","task_name":"Vision-Language Navigation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2308.04758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04758"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/defaultrui/bev-scene-graph","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran_violates":1,"ran_fixture":2,"ran":5,"ran_honours":1,"unverified":4},"by_repo_kind":{"official":{"samples":14,"ran":10,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":14,"samples":[{"code_sha256_prefix":"0f786c407fb1ee4c","entry":"swish","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/models/vilmodel_bev.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/models/vilmodel_bev.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"c362aaed2935ceff","entry":"calc_position_distance","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/models/graph_utils.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/models/graph_utils.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c362aaed2935ceff"}},{"code_sha256_prefix":"168e35f8ed1ad0ce","entry":"calculate_vp_rel_pos_fts","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/models/graph_utils.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/models/graph_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"168e35f8ed1ad0ce"}},{"code_sha256_prefix":"b4238358032237ee","entry":"construct_instrs","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/r2r/data_utils.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/r2r/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b4238358032237ee"}},{"code_sha256_prefix":"91e1742acf23aa57","entry":"extend_neg_masks","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/models/ops.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/models/ops.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91e1742acf23aa57"}},{"code_sha256_prefix":"fdc64f4c72036ae4","entry":"gelu","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/models/vilmodel_bev.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/models/vilmodel_bev.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"code_sha256_prefix":"d9c76c6dc9976905","entry":"gen_seq_masks","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/models/ops.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/models/ops.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d9c76c6dc9976905"}},{"code_sha256_prefix":"dac1993f5ce8e12e","entry":"get_angle_fts","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/models/graph_utils.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/models/graph_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dac1993f5ce8e12e"}},{"code_sha256_prefix":"80881fb0e12a6a8e","entry":"load_instr_datasets","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/r2r/data_utils.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/r2r/data_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"80881fb0e12a6a8e"}},{"code_sha256_prefix":"ea6c804876d1949c","entry":"postprocess_args","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/r2r/parser.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/r2r/parser.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea6c804876d1949c"}},{"code_sha256_prefix":"df2919fd1dad1d43","entry":"build_transformer","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/models/transformer.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/models/transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df2919fd1dad1d43"}},{"code_sha256_prefix":"7154bada41632ca4","entry":"create_transformer_encoder","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/models/ops.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/models/ops.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7154bada41632ca4"}},{"code_sha256_prefix":"ca1c94c8bdb81d00","entry":"get_tokenizer","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/models/vlnbert_bev_init.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/models/vlnbert_bev_init.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ca1c94c8bdb81d00"}},{"code_sha256_prefix":"7cd78050efefedf4","entry":"get_vlnbert_models","repo":"defaultrui/bev-scene-graph","repo_kind":"official","path":"bsg_vln/map_nav_src/models/vlnbert_bev_init.py","file_url":"https://github.com/defaultrui/bev-scene-graph/blob/HEAD/bsg_vln/map_nav_src/models/vlnbert_bev_init.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7cd78050efefedf4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}